© 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. 199767
    Prev
    Next
    INDEX
    Explanations

    foreign languages and scripts

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

    describing appearance or actions

    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
    一位
    0.52
    簍
    0.47
     находиться
    0.46
    াঙ্গ
    0.46
    體
    0.45
    㪕
    0.45
     funct
    0.44
     సంవత్సర
    0.44
     נמצא
    0.44
    績
    0.44
    POSITIVE LOGITS
     eyelashes
    0.49
    gares
    0.48
     earphones
    0.47
     flancs
    0.46
     eyebrows
    0.46
     ಕನ್ನಡ
    0.45
    vorschau
    0.45
     italiane
    0.45
    キ
    0.45
     italiano
    0.45
    Activations Density 0.001%

    No Known Activations