© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14723
    Prev
    Next
    INDEX
    Explanations

    Instead of

    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
    </b>
    -4.06
    ↵↵
    -3.22
    н
    -3.20
    </td>
    -2.77
    *
    -2.73
    ↵↵↵↵↵↵↵
    -2.63
    M
    -2.61
    -
    -2.58
    みたら
    -2.56
     "
    -2.55
    POSITIVE LOGITS
     uſed
    3.27
     pauv
    3.25
    酲
    2.84
     frança
    2.83
    髏
    2.78
     bleus
    2.77
    乀
    2.73
    ⢊
    2.64
    菪
    2.64
     multicolore
    2.61
    Activations Density 0.012%

    No Known Activations