© 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. 72906
    Prev
    Next
    INDEX
    Explanations

    numbered lists and stages

    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
     ſeveral
    -1.38
     Conſ
    -1.30
     jednod
    -1.25
     certainement
    -1.23
    ༼
    -1.21
     plafon
    -1.20
     rafraî
    -1.20
    ཥ
    -1.20
     Reglas
    -1.20
     coucher
    -1.20
    POSITIVE LOGITS
     or
    1.33
     uses
    1.31
     on
    1.28
     both
    1.26
     has
    1.21
     helps
    1.20
     with
    1.18
     at
    1.17
     like
    1.17
     E
    1.15
    Activations Density 0.001%

    No Known Activations