© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34608
    Prev
    Next
    INDEX
    Explanations

    Angstrom

    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
    Negative Logits
    ZIONE
    0.89
     осіб
    0.80
    ро
    0.75
    х
    0.75
    го
    0.73
     personalmente
    0.73
     linee
    0.71
    о
    0.71
    ка
    0.68
    餌
    0.68
    POSITIVE LOGITS
    皚
    0.92
    ுகிறது
    0.81
     vó
    0.80
     varieg
    0.78
    ஸ்
    0.75
    ointments
    0.73
    adilan
    0.73
     manchas
    0.73
    chien
    0.71
    涔
    0.71
    Activations Density 0.000%

    No Known Activations