© 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. 36135
    Prev
    Next
    INDEX
    Explanations

    population data and technology

    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
    にい
    0.51
     ентите
    0.47
    নিয়
    0.47
     scolded
    0.44
    Routed
    0.44
    珵
    0.43
    新しい
    0.43
     नाबाद
    0.43
    解決
    0.42
     mówi
    0.42
    POSITIVE LOGITS
    ())
    0.46
    1
    0.45
    re
    0.45
    severity
    0.45
    xture
    0.43
    on
    0.42
    conditional
    0.41
    reur
    0.41
     io
    0.40
     Severity
    0.40
    Activations Density 0.004%

    No Known Activations