© 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. 194535
    Prev
    Next
    INDEX
    Explanations

    after crashingtense muscles

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

    physical tension and verification

    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
    њ
    0.50
    ोसी
    0.50
    сла
    0.49
    린다
    0.49
    STUD
    0.47
    plemente
    0.46
    ेलकम
    0.46
    ⤠
    0.46
    ской
    0.46
    Evet
    0.46
    POSITIVE LOGITS
     Defensive
    0.47
    വ്ര
    0.45
     mobil
    0.44
     shot
    0.43
     hinzuf
    0.42
    yfikacja
    0.42
     died
    0.41
     langfrist
    0.41
     was
    0.40
     technisch
    0.40
    Activations Density 0.000%

    No Known Activations