© 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. 38667
    Prev
    Next
    INDEX
    Explanations

    religious and academic terms

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

    summarizing, translating, and remembering tasks

    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
     используются
    0.46
     கொண்டே
    0.46
     時
    0.46
    
    0.45
     אבל
    0.44
    ಲ
    0.44
     ))->
    0.43
     יל
    0.42
     בעי
    0.42
    時
    0.42
    POSITIVE LOGITS
     sabbatical
    0.53
     anest
    0.50
     mitig
    0.50
     liturgy
    0.49
     evidenced
    0.49
     liturgical
    0.49
     evangelical
    0.48
     epistem
    0.47
     apostolic
    0.46
     liturg
    0.46
    Activations Density 0.000%

    No Known Activations