Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 201
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ’
    -5.09
    ↵
    -3.23
    ’,
    -3.13
     With
    -2.69
        
    -2.44
    ه
    -2.38
    </em>
    -2.20
    In
    -2.20
     vorigen
    -2.16
     “
    -2.14
    POSITIVE LOGITS
    ・・・」
    2.69
    比如说
    2.47
    简约
    2.31
     greateſt
    2.13
    复古
    2.08
     sparkle
    2.08
    帮你
    2.08
     herbst
    2.08
    ους
    2.06
     scrutin
    2.06
    Activations Density 0.019%

    No Known Activations