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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118776
    Prev
    Next
    INDEX
    Explanations

    OAuth 2.0 authentication clients

    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_34/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
    lxt
    -0.80
    çalves
    -0.75
    dengan
    -0.73
    tdb
    -0.73
    برى
    -0.72
    atola
    -0.72
     Künst
    -0.72
     Näch
    -0.71
    лося
    -0.70
    angani
    -0.70
    POSITIVE LOGITS
    rif
    0.89
    مدل
    0.87
     clientele
    0.84
     برتر
    0.82
    idigung
    0.78
    ntilde
    0.78
    tifik
    0.77
    ônico
    0.77
    Stacey
    0.77
     clients
    0.76
    Activations Density 0.014%

    No Known Activations