© 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. 181966
    Prev
    Next
    INDEX
    Explanations

    market, taking note of examples

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

    individual system

    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
     injustices
    0.46
    一项
    0.44
     Violence
    0.43
     Eating
    0.43
     oppression
    0.43
    lilik
    0.42
    哔
    0.42
     somew
    0.42
     Tourism
    0.42
     Brain
    0.41
    POSITIVE LOGITS
    τέρα
    0.47
     कहलाता
    0.46
     চৈতন্যের
    0.44
    ologisk
    0.44
    ólogo
    0.44
     писатель
    0.44
    !);
    0.43
     emeritus
    0.43
    タイプの
    0.41
    ava
    0.41
    Activations Density 0.001%

    No Known Activations