© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9573
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     this
    -1.32
     of
    -1.31
     and
    -1.25
     or
    -1.21
     in
    -1.17
     by
    -1.10
     from
    -1.06
     Vorstand
    -1.02
     at
    -1.02
     during
    -0.97
    POSITIVE LOGITS
     waf
    1.15
    푉
    1.04
     KUN
    1.00
    制品
    1.00
     tambour
    1.00
     Broom
    1.00
     exhib
    0.99
     enro
    0.99
     Anſ
    0.98
    Gön
    0.98
    Activations Density 0.014%

    No Known Activations