© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42053
    Prev
    Next
    INDEX
    Explanations

    coding structure and parameters

    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
     тў
    0.92
    میں
    0.89
    ēl
    0.88
    ش
    0.85
     Я
    0.84
    ᓵ
    0.84
    ję
    0.83
    ў
    0.82
    ত
    0.82
    ază
    0.82
    POSITIVE LOGITS
     government
    0.89
     audacious
    0.88
     dubious
    0.85
     डिप्टी
    0.83
     vaguely
    0.82
     don
    0.82
     dodgy
    0.80
     partake
    0.80
     bespoke
    0.79
     jot
    0.77
    Activations Density 0.000%

    No Known Activations