© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3647
    Prev
    Next
    INDEX
    Explanations

    `a, b` assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     averigu
    2.41
    alho
    2.31
    araf
    2.31
    득
    2.22
    력을
    2.22
    Manipulation
    2.20
    ğraf
    2.19
     riot
    2.19
     neurologist
    2.19
    afd
    2.18
    POSITIVE LOGITS
     bilan
    0.89
    迹
    0.83
     existent
    0.82
    явление
    0.80
    碜
    0.79
     Corps
    0.75
    蹭
    0.73
     Име
    0.72
     existence
    0.69
     Thornton
    0.69
    Activations Density 0.018%

    No Known Activations