© 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. 40849
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Hlav
    0.88
    P
    0.83
     istilah
    0.80
    वत
    0.78
     gerais
    0.77
     teis
    0.77
     falei
    0.75
    )}\
    0.74
     күз
    0.74
     conjuntos
    0.73
    POSITIVE LOGITS
     acceptor
    0.73
    तु
    0.73
     acceptance
    0.71
    ubit
    0.69
    ړئ
    0.68
     electrolytic
    0.68
     retail
    0.66
     surrounding
    0.65
     opens
    0.64
     phosphorylation
    0.64
    Activations Density 0.000%

    No Known Activations