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. 22-GEMMASCOPE-RES-131K
    4. 12012
    Prev
    Next
    INDEX
    Explanations

    specific nouns and numbers

    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_22/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
    İZ
    -0.87
     inny
    -0.83
     minOccurs
    -0.82
    enters
    -0.81
    ったのは
    -0.79
    ryl
    -0.79
     blanche
    -0.79
    boné
    -0.77
     outfit
    -0.77
    かで
    -0.77
    POSITIVE LOGITS
     poshmark
    0.94
     فقط
    0.87
    Kali
    0.85
    nodata
    0.81
     eneste
    0.80
    Már
    0.78
    XIII
    0.77
    éma
    0.77
    Bila
    0.77
    TIP
    0.76
    Activations Density 0.007%

    No Known Activations