© 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. 1976
    Prev
    Next
    INDEX
    Explanations

    matrix C, parameters, name change

    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
     imprison
    0.53
     ネ
    0.48
    衅
    0.47
    ലെസ്
    0.46
     आत्म
    0.46
     yık
    0.46
     injustice
    0.45
     izaz
    0.45
    獄
    0.45
     injuring
    0.45
    POSITIVE LOGITS
    y
    0.60
    ي
    0.50
    i
    0.49
     Simulation
    0.48
    <0x83>
    0.45
    <0xBB>
    0.44
    m
    0.44
    لى
    0.44
     demod
    0.44
    بلغ
    0.43
    Activations Density 0.014%

    No Known Activations