© 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. 22-GEMMASCOPE-RES-131K
    7. 34728
    Prev
    Next
    INDEX
    Explanations

    spent duration

    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_22/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
     when
    -1.66
     what
    -1.53
     having
    -1.42
     which
    -1.42
     something
    -1.30
     that
    -1.30
     lancar
    -1.29
     beragam
    -1.24
     nonché
    -1.20
    憮
    -1.16
    POSITIVE LOGITS
     "}";
    1.31
     
    1.23
    unes
    1.18
     summers
    1.13
     Cómo
    1.05
     passend
    1.04
    part
    1.03
    ずっと
    1.02
    いっ
    1.02
    arise
    1.01
    Activations Density 0.024%

    No Known Activations