© 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. 28254
    Prev
    Next
    INDEX
    Explanations

    the greatest

    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
    a
    0.46
    ه
    0.45
    घन
    0.45
     dissociate
    0.45
    --)
    0.44
    gdf
    0.44
    @]
    0.43
     poi
    0.42
    애
    0.42
    ?)
    0.42
    POSITIVE LOGITS
    ovič
    0.50
    ullah
    0.47
    ificato
    0.47
    ennial
    0.46
    ikas
    0.46
    andan
    0.46
    ushal
    0.46
    atura
    0.45
     परंतु
    0.45
    ateboard
    0.45
    Activations Density 0.011%

    No Known Activations