© 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. 103205
    Prev
    Next
    INDEX
    Explanations

    as description

    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
     a
    -2.41
     adalah
    -1.79
     Weltkrieg
    -1.65
    嫫
    -1.60
     such
    -1.59
     something
    -1.54
     accompanying
    -1.52
    );
    -1.48
     är
    -1.47
     Minaj
    -1.42
    POSITIVE LOGITS
     you
    3.08
     they
    1.95
     we
    1.95
     it
    1.80
    他の
    1.46
    rité
    1.45
    ležité
    1.45
    是因为
    1.45
     biß
    1.41
    ILERS
    1.39
    Activations Density 0.047%

    No Known Activations