© 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. 41011
    Prev
    Next
    INDEX
    Explanations

    years past

    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
     dương
    0.71
    unico
    0.71
     gợi
    0.71
    czek
    0.69
    ка
    0.68
    parameters
    0.68
    ୃ
    0.68
     যাইহোক
    0.68
    лық
    0.66
    முறை
    0.65
    POSITIVE LOGITS
     aud
    0.93
    U
    0.88
    Ol
    0.86
    াড়ার
    0.85
    Y
    0.84
    াড়াও
    0.83
     auditors
    0.81
     idiot
    0.81
    Oc
    0.80
     angrily
    0.80
    Activations Density 0.000%

    No Known Activations