© 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. 184343
    Prev
    Next
    INDEX
    Explanations

    location names

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

    potential risks, genetic condition, targets casein, without added, robot paths

    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
    ENDAR
    0.54
     Баскетбол
    0.50
     bloc
    0.49
     bloco
    0.49
     numeri
    0.47
    ódulo
    0.47
    ℓ
    0.47
    SERVIDOR
    0.47
     liczba
    0.46
     contiguous
    0.46
    POSITIVE LOGITS
     عندما
    0.45
     Herrera
    0.45
    並沒有
    0.45
    ffine
    0.45
    NotIn
    0.43
     Cren
    0.43
    getitem
    0.42
    യ
    0.42
     In
    0.42
    讓人
    0.42
    Activations Density 0.001%

    No Known Activations