© 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. 143989
    Prev
    Next
    INDEX
    Explanations

    available through, read into, rewarded in, signals about

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

    pre-ejaculate fluid and clitoral stimulation

    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
     رض
    0.48
    statements
    0.48
    Data
    0.47
    p
    0.47
    hereinafter
    0.47
    后
    0.46
    раст
    0.45
    ोटेन
    0.45
    {
    0.45
    ia
    0.45
    POSITIVE LOGITS
     Seward
    0.46
     техники
    0.46
     imputation
    0.44
     Tjiwarl
    0.43
     ditth
    0.42
     colore
    0.42
     Kxc
    0.42
     convivial
    0.42
    )$;
    0.42
    Ŝ
    0.41
    Activations Density 0.000%

    No Known Activations