© 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. 65992
    Prev
    Next
    INDEX
    Explanations

    tokens after specific identifiers

    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
     suaves
    -1.07
     bailarina
    -1.06
     可愛い
    -1.02
    cciale
    -1.00
     ווע
    -0.98
    existsSync
    -0.97
    phol
    -0.96
     coloridos
    -0.95
    voted
    -0.95
    的他
    -0.94
    POSITIVE LOGITS
     XXVI
    1.02
    opsida
    1.02
     followed
    1.00
    ïde
    0.98
     '',
    0.96
    래스
    0.96
    来越
    0.95
    рення
    0.95
     would
    0.94
    льти
    0.91
    Activations Density 0.036%

    No Known Activations