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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101650
    Prev
    Next
    INDEX
    Explanations

    READ MORE

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

    The neuron fires on short uppercase “link” or section headings and captions (e.g. READ MORE:, PICTURES:, DIGGING FOR TOOLS:).

    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
     
    -1.11
    𝙅
    -1.08
     we
    -1.07
     actually
    -1.06
    ographics
    -1.02
    ↵↵↵↵
    -0.99
     ваш
    -0.98
    iguity
    -0.97
    ]
    -0.97
     would
    -0.96
    POSITIVE LOGITS
    vocations
    1.46
    melden
    1.45
     flexibles
    1.25
     compatibles
    1.24
     autres
    1.23
    sistence
    1.22
    considering
    1.20
    全体的に
    1.20
     imperio
    1.20
     generell
    1.19
    Activations Density 0.039%

    No Known Activations