© 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. 145972
    Prev
    Next
    INDEX
    Explanations

    foreign or special characters

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

    flagging and identifying violations

    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
     ifelse
    0.46
     enseignants
    0.46
     referenties
    0.44
     streamlines
    0.44
     Depends
    0.44
     asociaciones
    0.42
    䣨
    0.42
     analges
    0.42
     detract
    0.41
     Trabajo
    0.41
    POSITIVE LOGITS
    DE
    0.55
    ä
    0.55
    MAN
    0.49
    PER
    0.48
    ３
    0.46
    oj
    0.46
    yao
    0.46
    ホームページ
    0.46
    OU
    0.45
    ۳
    0.45
    Activations Density 0.000%

    No Known Activations