© 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. 179724
    Prev
    Next
    INDEX
    Explanations

    guarantee warrant point decrease abundance learning

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

    multilingual text snippets

    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
    anzit
    0.50
     Corr
    0.48
     Laub
    0.45
    ċ
    0.44
     Pří
    0.44
     Vine
    0.41
     منها
    0.41
     perdita
    0.41
     الحض
    0.40
     subgroups
    0.40
    POSITIVE LOGITS
    $',
    0.46
     bungee
    0.44
     공개
    0.43
    FRS
    0.43
    ร่าง
    0.43
    Referee
    0.42
    劾
    0.42
     olay
    0.42
    นิ
    0.41
    Oregon
    0.41
    Activations Density 0.001%

    No Known Activations