© 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. 34-GEMMASCOPE-RES-131K
    7. 84236
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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_34/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
     what
    -1.69
     in
    -1.46
     on
    -1.45
     at
    -1.25
     this
    -1.20
     any
    -1.20
     by
    -1.16
     ostensibly
    -1.14
     their
    -1.14
     epitom
    -1.11
    POSITIVE LOGITS
     entweder
    1.42
     alcune
    1.33
     diversos
    1.27
     poë
    1.12
    different
    1.10
     organizza
    1.10
    Posté
    1.09
    踅
    1.09
     cappuccio
    1.09
    Publié
    1.09
    Activations Density 0.005%

    No Known Activations