© 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-16K
    7. 13671
    Prev
    Next
    INDEX
    Explanations

    Phase I, Phone number

    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_16k_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
    an
    0.83
    a
    0.79
    t
    0.74
    v
    0.74
    tól
    0.66
    ją
    0.65
    r
    0.63
    he
    0.61
    m
    0.61
    as
    0.59
    POSITIVE LOGITS
    ب
    0.89
    ב
    0.83
    לו
    0.80
    س
    0.72
     orbit
    0.71
     excit
    0.70
    ли
    0.69
     entière
    0.68
    ’
    0.68
     isole
    0.68
    Activations Density 1.429%

    No Known Activations