© 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. 14131
    Prev
    Next
    INDEX
    Explanations

    religious and cooking contexts

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

    refusing explicit content

    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
    =
    0.57
    Y
    0.56
    H
    0.50
    h
    0.50
    Hö
    0.49
    vä
    0.49
    House
    0.48
    Heart
    0.47
    =(
    0.47
    Layout
    0.46
    POSITIVE LOGITS
     scelte
    0.51
    䒷
    0.51
    뻗
    0.50
     швид
    0.49
     przykład
    0.49
    ა
    0.48
     tấm
    0.47
    ến
    0.46
    rneğin
    0.46
     jeśli
    0.46
    Activations Density 0.000%

    No Known Activations