© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24053
    Prev
    Next
    INDEX
    Explanations

    "Why" questions and technique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raised
    0.37
     JSONObject
    0.37
     สํา
    0.36
     Cochrane
    0.36
    ☉
    0.36
     Meek
    0.35
     ಗ್ರಾಮ
    0.35
     {*}
    0.35
     trained
    0.34
    امه
    0.34
    POSITIVE LOGITS
    Alien
    0.43
    ಳು
    0.40
    Clothes
    0.40
    Deserial
    0.39
    Moreover
    0.37
     continua
    0.37
    面白い
    0.37
     Textiles
    0.36
     Textile
    0.36
     eerie
    0.36
    Activations Density 0.000%

    No Known Activations