© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26934
    Prev
    Next
    INDEX
    Explanations

    lengthy writings or speeches

    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
     at
    -1.31
    Some
    -1.10
     знаю
    -1.03
     hina
    -0.96
     with
    -0.95
     aware
    -0.94
    According
    -0.90
     representatives
    -0.90
     as
    -0.90
     glimpses
    -0.90
    POSITIVE LOGITS
     length
    1.70
    length
    1.52
     longest
    1.38
     длин
    1.28
     longer
    1.23
    argas
    1.21
     lunghezza
    1.20
     baterie
    1.18
    Length
    1.18
     lengthy
    1.17
    Activations Density 0.039%

    No Known Activations