© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20705
    Prev
    Next
    INDEX
    Explanations

    bile reflux

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    1.38
    that
    1.20
    ну
    1.17
    не
    1.06
    la
    1.05
    m
    1.02
    м
    1.00
    1
    1.00
    ların
    0.98
    should
    0.96
    POSITIVE LOGITS
    cco
    0.92
    cción
    0.91
    konom
    0.79
    getic
    0.79
    ffekt
    0.79
    hwar
    0.78
    instellungen
    0.77
    chten
    0.75
    volent
    0.73
    czki
    0.73
    Activations Density 2.006%

    No Known Activations