© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65043
    Prev
    Next
    INDEX
    Explanations

    alias, public

    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
     in
    -2.75
     (
    -2.75
     by
    -2.72
     all
    -2.53
     as
    -2.53
     to
    -2.48
     at
    -2.41
     on
    -2.34
     After
    -2.33
     for
    -2.31
    POSITIVE LOGITS
    ↵
    2.14
    ほとん
    1.97
     étan
    1.95
     inond
    1.89
     実例
    1.88
     prachtige
    1.88
     nieuwe
    1.84
     réfrig
    1.84
     nuest
    1.80
    änderungen
    1.80
    Activations Density 0.016%

    No Known Activations