© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15946
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     of
    -1.63
    Y
    -1.28
     However
    -1.27
    The
    -1.22
    It
    -1.20
    m
    -1.15
    M
    -1.13
     the
    -1.13
     that
    -1.12
     Therefore
    -1.10
    POSITIVE LOGITS
     может
    1.33
    èles
    1.30
     اگر
    1.29
    FONTE
    1.25
    pography
    1.21
     }-
    1.21
    ：
    1.18
    ！！！！
    1.17
    şil
    1.17
    ！(
    1.16
    Activations Density 0.131%

    No Known Activations