© 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. 233362
    Prev
    Next
    INDEX
    Explanations

    child sexual exploitation

    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
    espół
    0.47
     Carrick
    0.46
    prising
    0.46
    定的
    0.46
     Gó
    0.45
    benzyl
    0.45
    teness
    0.44
    仹
    0.44
    DbContext
    0.44
     বাসিন্দা
    0.44
    POSITIVE LOGITS
     CANT
    0.47
     fer
    0.47
    েস
    0.47
     PHIL
    0.47
    ನೇ
    0.46
     markets
    0.46
     NAP
    0.46
     GY
    0.46
     SUPPL
    0.45
     commodities
    0.44
    Activations Density 0.000%

    No Known Activations