© 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. 41001
    Prev
    Next
    INDEX
    Explanations

    integer representations (e.g., 8-bit)

    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
     στό
    0.79
     ['.
    0.74
    ud
    0.73
    '%
    0.73
     Solver
    0.73
     прежде
    0.72
    〈
    0.72
    妳
    0.71
    ლი
    0.71
    에
    0.70
    POSITIVE LOGITS
    ز
    1.16
    निर्भर
    0.87
     memperoleh
    0.86
    عة
    0.84
    parte
    0.83
    کس
    0.82
    et
    0.82
     Beberapa
    0.81
    Civita
    0.80
    其他
    0.79
    Activations Density 0.000%

    No Known Activations