© 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. 30569
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    sexually suggestive conversations

    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
     ISD
    0.43
    dis
    0.43
    short
    0.43
    hit
    0.43
    a
    0.42
    zz
    0.42
    sur
    0.42
    begin
    0.41
    w
    0.41
    jeff
    0.41
    POSITIVE LOGITS
     cérémon
    0.55
     variétés
    0.55
    စိတ်အပိုင်း
    0.52
     homenaje
    0.49
     vallée
    0.49
     nue
    0.48
     và
    0.47
    ヨーク
    0.47
     alá
    0.46
     escultura
    0.46
    Activations Density 0.000%

    No Known Activations