© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 152259
    Prev
    Next
    INDEX
    Explanations

    Icelandic, spouse, motorway, alphabet

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

    corporal punishment and spanking

    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
    ,
    0.72
     The
    0.54
     A
    0.52
    ).
    0.51
    <em>
    0.49
    )
    0.48
     Hội
    0.47
     Cox
    0.47
    /
    0.47
     Herzog
    0.47
    POSITIVE LOGITS
    ANNEL
    0.53
    assanam
    0.53
    ABASE
    0.52
    apayati
    0.50
    RENCH
    0.49
    loggedIn
    0.49
    sschutz
    0.49
    andidate
    0.48
     लकार
    0.48
    stdout
    0.48
    Activations Density 0.001%

    No Known Activations