© 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. 128823
    Prev
    Next
    INDEX
    Explanations

    standard deviation and variance

    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
     Fälle
    -1.37
     Gespräche
    -1.34
     chiesa
    -1.33
    νονται
    -1.31
    鈈
    -1.30
     ristor
    -1.26
     minore
    -1.26
     mangiare
    -1.21
     jardim
    -1.20
     出演
    -1.20
    POSITIVE LOGITS
     of
    1.93
     årets
    1.49
     we
    1.40
     externas
    1.39
     geweldig
    1.36
    To
    1.27
     poniżej
    1.23
     techniczne
    1.20
     rozwo
    1.19
     móds
    1.17
    Activations Density 0.017%

    No Known Activations