© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89416
    Prev
    Next
    INDEX
    Explanations

    positions, avoidance, regularly, pollution

    np_acts-logits-general · gemini-2.5-flash-lite

    dishes or religions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     unrelenting
    0.42
     механизм
    0.42
     отношение
    0.41
    律
    0.41
     relentless
    0.41
     transpar
    0.40
     transparence
    0.40
     механиз
    0.40
     unfor
    0.39
     символ
    0.39
    POSITIVE LOGITS
    Pid
    0.48
    THREE
    0.47
     ପ
    0.45
    etah
    0.44
    Xem
    0.44
     大学
    0.44
     छुट्टियों
    0.44
    Ej
    0.43
    Permissions
    0.43
    kich
    0.43
    Activations Density 0.002%

    No Known Activations