© 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. 95045
    Prev
    Next
    INDEX
    Explanations

    child branch terms society ways

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

    lead magnets

    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
     tr
    0.48
    </b>
    0.44
     speaker
    0.43
     speakers
    0.43
     hundreds
    0.43
     united
    0.43
    ,
    0.43
     dialed
    0.43
     latex
    0.42
    erede
    0.41
    POSITIVE LOGITS
    ৤
    0.52
    mAvailable
    0.49
    മുണ്ട്
    0.48
     بنابراین
    0.48
     Ressourcen
    0.48
    ༺
    0.47
    িকের
    0.47
     পরিকল্পনা
    0.46
     জমি
    0.46
    Ⴚ
    0.46
    Activations Density 0.000%

    No Known Activations