© 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. 30308
    Prev
    Next
    INDEX
    Explanations

    gambling, betting, casino

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

    data protection legislation

    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
     Molecular
    0.41
     Medicine
    0.38
     the
    0.38
    ,\\
    0.37
     cells
    0.36
     was
    0.36
    ,
    0.36
     vertebrate
    0.35
     of
    0.35
     Creek
    0.35
    POSITIVE LOGITS
     вполне
    0.42
     imprescind
    0.41
    <unused2044>
    0.40
     смогли
    0.40
    <unused506>
    0.38
    también
    0.37
    роваться
    0.36
     शिंदे
    0.36
    ᚗ
    0.36
    <unused1095>
    0.35
    Activations Density 0.002%

    No Known Activations