© 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. 44309
    Prev
    Next
    INDEX
    Explanations

    declarations, contiguous, delivery

    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
    Prot
    0.89
    Tangent
    0.83
    నీ
    0.78
    Listing
    0.77
    Hyundai
    0.76
    Mens
    0.75
    唿
    0.75
    Baik
    0.75
     Под
    0.74
    HI
    0.73
    POSITIVE LOGITS
    つの
    1.02
    wso
    0.88
    aba
    0.86
     lively
    0.86
    continues
    0.85
    ht
    0.84
    ides
    0.83
     ange
    0.83
     ona
    0.83
    𝕦
    0.83
    Activations Density 0.000%

    No Known Activations