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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14746
    Prev
    Next
    INDEX
    Explanations

    key, sdk, version, update, coefficients

    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_31_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
    opend
    0.62
    Android
    0.61
    Parking
    0.60
    喜
    0.59
    Nel
    0.56
    Man
    0.54
    Ref
    0.54
    ᕼ
    0.53
    Mal
    0.53
    Decoration
    0.53
    POSITIVE LOGITS
     templates
    0.64
    βολ
    0.61
     coefficients
    0.60
     Coefficients
    0.60
     coefficient
    0.58
     buck
    0.57
     bol
    0.55
     mongo
    0.54
     template
    0.54
    ்துறை
    0.54
    Activations Density 0.030%

    No Known Activations