© 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. 70732
    Prev
    Next
    INDEX
    Explanations

    history and contexts

    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
    ⩴
    -1.19
    )]
    -1.15
    ",
    -1.11
    ',
    -1.07
    icata
    -1.04
     äusser
    -0.99
    Fifteen
    -0.98
    enderal
    -0.98
     étroite
    -0.98
     sospe
    -0.97
    POSITIVE LOGITS
     history
    1.76
     historians
    1.42
    historical
    1.34
     histories
    1.33
    history
    1.27
     ragu
    1.27
     sement
    1.27
     gången
    1.27
     dager
    1.21
     of
    1.20
    Activations Density 0.027%

    No Known Activations