© 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. 10168
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

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

    proper nouns, particularly names of people and places (especially Indian locations and political/scientific figures).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron responds to capitalized tokens—i.e. proper names, places, organizations, or other named‐entity terms.

    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
    ✁
    -2.78
    ⵌ
    -2.64
    preneurs
    -2.58
     hinzugefügt
    -2.50
    пература
    -2.45
    ensões
    -2.38
    愎
    -2.36
    諶
    -2.33
    ⚬
    -2.33
     alfabe
    -2.33
    POSITIVE LOGITS
    ↵
    3.36
    io
    2.91
     The
    2.84
    t
    2.75
    ку
    2.63
     We
    2.53
    The
    2.52
    ]
    2.50
    They
    2.48
    <em>
    2.47
    Activations Density 0.064%

    No Known Activations