© 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. 110640
    Prev
    Next
    INDEX
    Explanations

    university & affiliations

    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
     Unpublished
    -0.96
     downright
    -0.91
    gione
    -0.90
    transmitters
    -0.89
     सुन
    -0.88
     hotline
    -0.88
    метров
    -0.88
     ibunya
    -0.85
     frankly
    -0.85
    unl
    -0.84
    POSITIVE LOGITS
    是啊
    1.08
     soziale
    1.06
     politische
    1.00
    بیشتر
    1.00
     betrachtet
    0.98
    jenige
    0.96
    ppin
    0.93
     gestartet
    0.93
     iedereen
    0.92
     pequeñas
    0.91
    Activations Density 0.009%

    No Known Activations