© 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. 212569
    Prev
    Next
    INDEX
    Explanations

    imports, promotional, forced, scope

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

    data sensitivity

    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
     Hø
    0.49
    徥
    0.48
     spør
    0.47
    Fcm
    0.46
     लापता
    0.46
     İm
    0.45
     Gh
    0.45
     hör
    0.45
     svare
    0.44
     unbel
    0.44
    POSITIVE LOGITS
    ：
    0.45
    mime
    0.45
     আইন
    0.44
     রাইফেল
    0.44
    SCOPE
    0.43
     этого
    0.42
     examiners
    0.42
     PRICES
    0.42
    力度
    0.42
     размеры
    0.42
    Activations Density 0.003%

    No Known Activations