© 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. 95668
    Prev
    Next
    INDEX
    Explanations

    . or :: format

    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
     one
    -1.53
     with
    -1.49
     in
    -1.42
     and
    -1.35
     all
    -1.32
     like
    -1.30
     more
    -1.30
     through
    -1.25
     this
    -1.25
     at
    -1.25
    POSITIVE LOGITS
    ⅖
    1.38
    ⅗
    1.27
     ARISING
    1.27
     wille
    1.23
    ౭
    1.21
     rafraî
    1.20
     fermer
    1.19
     DURING
    1.16
     constitue
    1.16
    镲
    1.14
    Activations Density 0.008%

    No Known Activations