© 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. 128240
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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
    <em>
    -1.16
    <strong>
    -1.13
     
    -1.00
     The
    -1.00
     of
    -0.99
      
    -0.98
     for
    -0.97
    plr
    -0.97
    *
    -0.95
     (
    -0.93
    POSITIVE LOGITS
    Kontra
    1.41
    Reak
    1.30
    Komentar
    1.23
     mân
    1.22
    Karten
    1.13
     profondità
    1.13
    Čo
    1.12
     discussione
    1.12
     ragazza
    1.09
    Kamera
    1.09
    Activations Density 0.038%

    No Known Activations