© 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. 36207
    Prev
    Next
    INDEX
    Explanations

    time ranges

    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
     Hölder
    0.99
     һ
    0.99
    dır
    0.95
     kanë
    0.94
    𝑧
    0.94
     τ
    0.89
     Архів
    0.89
    冂
    0.89
     λ
    0.87
     ϒ
    0.87
    POSITIVE LOGITS
    '
    0.78
     blows
    0.75
    வசாய
    0.72
    RA
    0.70
    불어
    0.70
    ari
    0.67
    ference
    0.65
    пута
    0.65
    ளது
    0.64
     élect
    0.63
    Activations Density 0.000%

    No Known Activations