© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39216
    Prev
    Next
    INDEX
    Explanations

    function return values

    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
    instead
    -1.20
    dames
    -1.14
    announced
    -1.13
     kabát
    -1.12
     célè
    -1.10
    ghh
    -1.09
    received
    -1.05
     TÉ
    -1.05
    tomato
    -1.03
    casing
    -1.02
    POSITIVE LOGITS
     this
    1.14
     did
    1.09
     could
    1.05
     themselves
    1.01
     didn
    1.00
     success
    1.00
     may
    1.00
     concerned
    0.98
    </th>
    0.98
    はお
    0.97
    Activations Density 0.002%

    No Known Activations