© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6746
    Prev
    Next
    INDEX
    Explanations

    nearest girl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     Says
    0.82
    ad
    0.75
     RESP
    0.75
    ült
    0.74
    lation
    0.73
    w
    0.71
    ”?
    0.71
     Siren
    0.71
    ”).
    0.71
     dotyczą
    0.71
    POSITIVE LOGITS
    م
    1.24
    د
    1.20
    ب
    1.20
    ATION
    1.09
    ية
    1.03
    ع
    1.03
    ный
    1.02
    ح
    1.00
    IN
    0.98
    ت
    0.97
    Activations Density 0.000%

    No Known Activations