© 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-262K
    7. 39926
    Prev
    Next
    INDEX
    Explanations

    specific entities followed by description

    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_262k_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
    %
    0.46
    vent
    0.44
    ti
    0.44
    ta
    0.41
    pping
    0.40
    schen
    0.40
    ž
    0.40
     sebanyak
    0.39
    ?
    0.39
    var
    0.39
    POSITIVE LOGITS
    묭
    0.51
    Directories
    0.49
    ાવી
    0.49
     karenge
    0.48
    하시는
    0.47
    曈
    0.47
     couches
    0.46
     сиз
    0.46
    ﾁ
    0.46
     housewives
    0.46
    Activations Density 0.000%

    No Known Activations