© 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. 44471
    Prev
    Next
    INDEX
    Explanations

    numbers followed by such

    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
     radiology
    0.91
    ton
    0.89
    y
    0.89
     succession
    0.85
     preservation
    0.84
    S
    0.81
    ↵
    0.80
     Radiology
    0.80
    RI
    0.79
     germination
    0.79
    POSITIVE LOGITS
     cuáles
    0.96
     entraîne
    0.96
    きた
    0.95
     autént
    0.91
    виться
    0.91
    ćeg
    0.91
     respectivos
    0.90
    /=
    0.90
     waarin
    0.89
     encontrarás
    0.89
    Activations Density 0.000%

    No Known Activations