© 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. 145020
    Prev
    Next
    INDEX
    Explanations

    slow with, nest box

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

    predicting comparisons

    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
     ის
    0.49
    过于
    0.46
     say
    0.45
    ed
    0.44
    o
    0.43
     אס
    0.43
     der
    0.43
     dear
    0.43
     exec
    0.41
    s
    0.41
    POSITIVE LOGITS
    振動
    0.52
    مكن
    0.51
    AKT
    0.50
    銷
    0.49
    essoa
    0.48
    煞
    0.47
     vibrates
    0.45
    હા
    0.45
    混沌
    0.44
    血管
    0.44
    Activations Density 0.002%

    No Known Activations