© 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. 132388
    Prev
    Next
    INDEX
    Explanations

    action verbs: pickup, blasted, learn, discover

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

    sexual abuse

    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
    งาม
    0.46
    ਬ
    0.46
    .".
    0.45
    льній
    0.44
    .”.
    0.44
     représ
    0.44
    สู่
    0.43
    笺
    0.43
     appelé
    0.42
    浜
    0.42
    POSITIVE LOGITS
     زر
    0.47
    ETARY
    0.46
    ingar
    0.46
    igat
    0.46
    uner
    0.45
     учу
    0.45
     mine
    0.45
    a
    0.45
     dub
    0.44
     mina
    0.44
    Activations Density 0.000%

    No Known Activations