© 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. 37778
    Prev
    Next
    INDEX
    Explanations

    safety warnings and specific details

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

    registration period

    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
     ووٹ
    0.49
    obiettivo
    0.46
    合計
    0.44
    hado
    0.44
    Asked
    0.44
    諦
    0.44
     выбра
    0.44
    具体的な
    0.43
     رفض
    0.42
    買
    0.42
    POSITIVE LOGITS
    危险
    0.46
     safer
    0.44
     hypertext
    0.43
     వైద్య
    0.42
     Covid
    0.42
     hazardous
    0.41
     सहायता
    0.41
     cache
    0.41
    bathing
    0.41
     Tasting
    0.40
    Activations Density 0.000%

    No Known Activations