© 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. 26425
    Prev
    Next
    INDEX
    Explanations

    information provided by

    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
     étendue
    -1.02
    ENCIL
    -1.00
    rinted
    -0.99
    witter
    -0.99
     aŭ
    -0.90
     المتح
    -0.90
     dAtA
    -0.88
    ｳ
    -0.88
    licants
    -0.88
     expectativas
    -0.87
    POSITIVE LOGITS
     provided
    1.22
     offered
    1.12
     by
    0.93
    autumn
    0.89
    vano
    0.87
     documents
    0.87
     to
    0.85
    ischer
    0.84
    ほうが
    0.83
     kindly
    0.83
    Activations Density 0.034%

    No Known Activations