© 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. 15947
    Prev
    Next
    INDEX
    Explanations

    special character followed by word

    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
    tament
    -0.87
     olika
    -0.86
     étaient
    -0.86
    MainThread
    -0.85
     jugadores
    -0.84
    REAM
    -0.84
     FIM
    -0.83
    intos
    -0.83
    õe
    -0.83
    siasme
    -0.83
    POSITIVE LOGITS
     literally
    0.84
     under
    0.81
     appears
    0.78
     apparently
    0.78
    雜
    0.78
    acruz
    0.77
     seems
    0.77
     can
    0.77
    هب
    0.76
     anywhere
    0.75
    Activations Density 0.041%

    No Known Activations