© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130794
    Prev
    Next
    INDEX
    Explanations

    ofSpiritarg

    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
    leren
    -1.16
    irnov
    -1.15
     ISSUED
    -1.14
     regata
    -1.13
     alcool
    -1.13
     motocicleta
    -1.13
    หรือ
    -1.10
     apartament
    -1.09
     tigre
    -1.07
     RISERV
    -1.07
    POSITIVE LOGITS
    b
    1.47
    ing
    1.45
    D
    1.43
    で見る
    1.38
    N
    1.37
    S
    1.36
    E
    1.34
    M
    1.32
    T
    1.30
    H
    1.30
    Activations Density 0.000%

    No Known Activations