© 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. 98376
    Prev
    Next
    INDEX
    Explanations

    counts and metrics

    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
     and
    -1.48
     as
    -1.26
     arba
    -1.23
     an
    -1.22
    J
    -1.20
    N
    -1.19
     while
    -1.18
     or
    -1.17
     that
    -1.16
     a
    -1.13
    POSITIVE LOGITS
     даже
    1.24
     incluindo
    1.21
     parlent
    1.16
     Después
    1.16
     gewährle
    1.16
     découvrez
    1.15
     falando
    1.13
    嚆
    1.13
     começaram
    1.13
    実際に
    1.12
    Activations Density 0.045%

    No Known Activations