© 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. 42490
    Prev
    Next
    INDEX
    Explanations

    help/many/which/very followed by other words

    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
     just
    1.02
     stupid
    0.98
     H
    0.98
     wären
    0.97
     south
    0.96
     upped
    0.94
     hätte
    0.94
     villes
    0.94
     año
    0.93
     southern
    0.93
    POSITIVE LOGITS
    ்கலை
    1.20
    ്‍
    1.20
    с
    1.19
     מר
    1.18
    play
    1.16
    adores
    1.14
    О
    1.12
    <unused2130>
    1.12
    <unused2172>
    1.12
    imagem
    1.09
    Activations Density 0.001%

    No Known Activations