© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7950
    Prev
    Next
    INDEX
    Explanations

    mountain top

    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_16k_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
    tch
    2.17
     таки
    1.98
     וע
    1.97
    き
    1.92
    ture
    1.85
    畔
    1.78
    רים
    1.77
    сное
    1.76
    <0xA0>
    1.70
    いただける
    1.70
    POSITIVE LOGITS
    unprocessable
    2.08
    AM
    2.03
    ce
    1.96
     marshmallows
    1.95
    seriously
    1.91
    för
    1.90
    ächlich
    1.88
     saben
    1.88
    ද්ග
    1.86
    ET
    1.85
    Activations Density 0.061%

    No Known Activations