© 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. 128903
    Prev
    Next
    INDEX
    Explanations

    punctuation and allot

    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
    Fakta
    -1.94
    Struktur
    -1.90
    Karakter
    -1.89
    Lá
    -1.84
     pertaining
    -1.80
    Reak
    -1.75
    というわけで
    -1.70
    Donativos
    -1.70
    Läh
    -1.70
     venturing
    -1.70
    POSITIVE LOGITS
     '"
    1.91
     "'
    1.81
     '-
    1.76
     '
    1.75
    ?"
    1.74
    та
    1.67
    we
    1.66
    ",
    1.65
    %"),
    1.62
     unbelievably
    1.60
    Activations Density 0.136%

    No Known Activations