Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6396
    Prev
    Next
    INDEX
    Explanations

    aligning with concepts

    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
    ली
    2.09
    lerine
    1.95
    нец
    1.94
    lerinde
    1.83
     Extremely
    1.81
    URATION
    1.79
    וש
    1.78
    囲
    1.75
     ECO
    1.74
    lipid
    1.73
    POSITIVE LOGITS
    el
    2.36
    ant
    1.92
    ز
    1.91
    ان
    1.90
    am
    1.84
     bepaalde
    1.83
    ির
    1.82
    ıları
    1.81
    대
    1.81
     justamente
    1.80
    Activations Density 0.018%

    No Known Activations