© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129303
    Prev
    Next
    INDEX
    Explanations

    deciduous and temperate forests

    np_acts-logits-general · gemini-2.5-flash-lite

    places or environments, particularly geographic locations like "Salisbury" and types of forests (deciduous, temperate).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on technical classification names and formal proper‐noun labels—e.g. habitat descriptors like “deciduous,” “temperate,” “forests” and place-names like “Salisbury.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鱨
    -2.92
    鬭
    -2.86
    嫱
    -2.83
    韡
    -2.64
    鼉
    -2.63
    蹑
    -2.58
    拶
    -2.55
     És
    -2.55
    ⧠
    -2.52
    ⸨
    -2.48
    POSITIVE LOGITS
    l
    2.64
    ↵↵
    2.63
    t
    2.56
     як
    2.53
    на
    2.52
    }=\
    2.42
    ”-
    2.42
    rostis
    2.38
     edgy
    2.23
    2.22
    Activations Density 0.012%

    No Known Activations