© 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. 36851
    Prev
    Next
    INDEX
    Explanations

    gaming and betting terms

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

    expectation and substance

    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
    ni
    0.64
    l
    0.59
    av
    0.54
    m
    0.53
    in
    0.52
    migration
    0.52
    u
    0.52
    ist
    0.52
    c
    0.52
    lh
    0.51
    POSITIVE LOGITS
     पुराण
    0.50
     HONOR
    0.48
     Resultados
    0.48
     Бет
    0.45
     бет
    0.45
     بیټ
    0.44
    जिंग
    0.42
     वैलेंट
    0.42
     सेल्फ
    0.42
     अपडेट
    0.41
    Activations Density 0.000%

    No Known Activations