© 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. 7921
    Prev
    Next
    INDEX
    Explanations

    excitement and anticipation

    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
    ،
    0.57
    -
    0.54
    ,
    0.52
     tetap
    0.49
     ternyata
    0.42
     trés
    0.42
    ፣
    0.42
    ，
    0.42
    OOL
    0.41
     telepon
    0.40
    POSITIVE LOGITS
    ات
    0.61
    ের
    0.61
    ों
    0.60
    ان
    0.57
    ס
    0.56
    sag
    0.54
    cí
    0.52
    s
    0.52
    स
    0.48
    ट
    0.48
    Activations Density 0.270%

    No Known Activations