© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111783
    Prev
    Next
    INDEX
    Explanations

    advice for, uncontrolled secondary, equip each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    谘
    -1.59
     When
    -1.53
     nuestros
    -1.49
     estos
    -1.49
     these
    -1.43
     когато
    -1.41
    When
    -1.40
     on
    -1.40
    することも
    -1.34
     twelve
    -1.33
    POSITIVE LOGITS
     then
    1.70
     such
    1.61
     garten
    1.48
    ländischen
    1.43
    Показать
    1.40
    чно
    1.38
    ⨯
    1.35
    まずは
    1.34
    gether
    1.32
     munich
    1.31
    Activations Density 0.195%

    No Known Activations