© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24121
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    comments starting with #

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    佞
    0.42
    オス
    0.41
    允
    0.40
     ②
    0.40
     ioutil
    0.40
    Issuer
    0.39
     orthon
    0.39
     refute
    0.39
    ంబేద్
    0.39
    முகச்
    0.39
    POSITIVE LOGITS
    {\"
    0.45
    miller
    0.44
    easter
    0.43
    leg
    0.43
    0.43
    gist
    0.41
    wani
    0.40
    empatan
    0.40
    christ
    0.40
     СПб
    0.40
    Activations Density 0.004%

    No Known Activations