© 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. 35007
    Prev
    Next
    INDEX
    Explanations

    URLs and descriptions

    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
     on
    -1.28
     with
    -1.27
    lowa
    -1.21
     without
    -1.16
    🐾
    -1.12
     maand
    -1.09
     it
    -1.06
    🤤
    -1.03
    DONALD
    -1.02
    )))))
    -1.01
    POSITIVE LOGITS
     accél
    1.25
     montrer
    1.24
     nová
    1.18
     fundamentos
    1.09
     establecidos
    1.09
    licos
    1.08
    こういった
    1.08
    それにしても
    1.05
     .\
    1.05
    Literatuur
    1.05
    Activations Density 0.054%

    No Known Activations