© 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. 193342
    Prev
    Next
    INDEX
    Explanations

    locations and entities followed by descriptions

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

    societal isolation and judgment

    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
     সারা
    0.58
    今天要
    0.51
     Canva
    0.49
    Vậy
    0.48
    廡
    0.46
    vät
    0.46
    綃
    0.46
    আজ
    0.45
    ড
    0.45
    作为
    0.45
    POSITIVE LOGITS
     ஈடுப
    0.45
     perspectivas
    0.44
    5
    0.43
     redd
    0.43
     juris
    0.42
     recklessly
    0.42
     confiar
    0.42
     walnuts
    0.42
     violates
    0.42
     giurid
    0.41
    Activations Density 0.002%

    No Known Activations