© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78590
    Prev
    Next
    INDEX
    Explanations

    describing states or relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     grammaticality
    0.49
    กีฬา
    0.48
    ઓ
    0.47
    قت
    0.46
    合适的
    0.45
    怖い
    0.45
    ശാസ്ത്ര
    0.44
    CubeSize
    0.44
    サラダ
    0.44
    ною
    0.43
    POSITIVE LOGITS
     s
    0.53
    ,
    0.52
     represent
    0.51
     représentent
    0.51
     den
    0.49
    :
    0.49
     v
    0.48
     .
    0.47
     nej
    0.45
    <start_of_image>
    0.45
    Activations Density 0.014%

    No Known Activations