© 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-262K
    7. 2639
    Prev
    Next
    INDEX
    Explanations

    URLs linking to products, downloads, or search results

    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
     T
    0.82
    ς
    0.79
    ן
    0.72
     J
    0.71
    ctive
    0.68
     would
    0.68
     vezes
    0.66
    ECTION
    0.66
    𝐈
    0.65
     गर
    0.64
    POSITIVE LOGITS
    とめ
    0.86
    те
    0.74
    ată
    0.73
    árl
    0.73
     phishing
    0.72
    тың
    0.72
     Cáceres
    0.71
    ícias
    0.71
     doings
    0.70
    quête
    0.69
    Activations Density 0.018%

    No Known Activations