© 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. 33129
    Prev
    Next
    INDEX
    Explanations

    indecent assault | variety of | luster

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

    cross-origin resource sharing

    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
    羰
    0.49
    ezi
    0.48
    膿
    0.47
    BottomOf
    0.47
    ErrorInfo
    0.47
    жено
    0.46
    RationalValue
    0.46
    ﻅ
    0.45
    VideoButton
    0.45
     LoginPage
    0.45
    POSITIVE LOGITS
    ਸ
    0.44
     pans
    0.43
    ਮ
    0.42
     progenitor
    0.41
     lifetime
    0.40
    .
    0.40
    lite
    0.40
    fields
    0.39
    straight
    0.39
     transitions
    0.39
    Activations Density 0.000%

    No Known Activations