© 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. 27606
    Prev
    Next
    INDEX
    Explanations

    positive exclamations and approval

    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
    鼕
    -1.26
    filosof
    -1.23
     inteligen
    -1.18
    sandal
    -1.18
    sailor
    -1.17
    lulu
    -1.15
    dür
    -1.14
     rezerv
    -1.13
     biela
    -1.13
     Änderungen
    -1.12
    POSITIVE LOGITS
    !
    1.75
     that
    1.68
    Finally
    1.26
     finally
    1.23
    那就
    1.19
    finally
    1.15
    that
    1.13
    more
    1.13
    p
    1.13
    //
    1.10
    Activations Density 0.014%

    No Known Activations