© 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. 86824
    Prev
    Next
    INDEX
    Explanations

    Matilda, nuisance, father, revolve around

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

    statements, values, responses

    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
     jaren
    0.45
     Primeiro
    0.45
    inec
    0.45
    騰
    0.44
     lignes
    0.43
     panini
    0.43
     giornata
    0.43
    ají
    0.43
    右手
    0.43
    জিব
    0.42
    POSITIVE LOGITS
    하거나
    0.42
    produk
    0.41
    மம்
    0.41
    䇢
    0.40
     olabilir
    0.40
    ですから
    0.40
    ָד
    0.39
     fledgling
    0.39
    рода
    0.39
    
    0.38
    Activations Density 0.001%

    No Known Activations