© 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. 24773
    Prev
    Next
    INDEX
    Explanations

    places and people

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

    exact date, time, description, definition

    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
    る
    0.49
    嘴
    0.46
     SM
    0.45
    不同的
    0.45
    мон
    0.44
     海
    0.43
     Sea
    0.43
     Ups
    0.43
     disapproved
    0.42
    ベル
    0.42
    POSITIVE LOGITS
    сшта
    0.45
     സെക്രട്ട
    0.45
     første
    0.44
     niiden
    0.43
    recieve
    0.43
     ihre
    0.42
     privat
    0.42
     $:=$
    0.42
    umbnail
    0.41
     verdient
    0.41
    Activations Density 0.000%

    No Known Activations