© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61005
    Prev
    Next
    INDEX
    Explanations

    status bar

    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_10/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
     sisält
    -1.55
     those
    -1.51
     cuyas
    -1.48
    쨩
    -1.45
    ouverture
    -1.44
     cuyos
    -1.42
     jenen
    -1.40
    がる
    -1.35
     asociada
    -1.35
     between
    -1.34
    POSITIVE LOGITS
    status
    1.92
     status
    1.76
     STATUS
    1.66
     "..\..\
    1.61
    
    1.59
    on
    1.56
    Status
    1.52
     на
    1.52
    焢
    1.50
    providedIn
    1.49
    Activations Density 0.027%

    No Known Activations