© 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. 89748
    Prev
    Next
    INDEX
    Explanations

    non-invasive skin applications

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

    controlling critical resources

    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
    論文
    0.43
    anay
    0.43
    扨
    0.42
     സു
    0.42
     সাহেবের
    0.41
     operations
    0.41
    슈
    0.41
     निजी
    0.40
     Circular
    0.40
     ત્યાં
    0.40
    POSITIVE LOGITS
    llen
    0.56
    +]
    0.54
     :]
    0.52
    بول
    0.52
     देशभ
    0.52
    Z
    0.51
    +)
    0.49
    imbabwe
    0.48
    Ζ
    0.48
     Z
    0.48
    Activations Density 0.001%

    No Known Activations