© 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. 6185
    Prev
    Next
    INDEX
    Explanations

    complex descriptive words

    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
    im
    1.59
    ва
    1.54
    it
    1.52
    genres
    1.47
    imizi
    1.44
    ab
    1.39
    िन
    1.35
    م
    1.35
    ok
    1.30
    profits
    1.30
    POSITIVE LOGITS
     esquerda
    1.41
    FUL
    1.41
    Պ
    1.39
    FULLY
    1.36
    И
    1.28
    деся
    1.27
     Па
    1.26
    기를
    1.22
    ς
    1.21
    क
    1.20
    Activations Density 2.477%

    No Known Activations