© 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. 110596
    Prev
    Next
    INDEX
    Explanations

    residing in locations

    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
    yyyyy
    -0.92
    Cartney
    -0.85
     Logistik
    -0.83
    hline
    -0.78
     Optik
    -0.77
    🤬
    -0.76
     Fulda
    -0.76
     Guayaquil
    -0.75
     Rhodesia
    -0.75
    ，”
    -0.75
    POSITIVE LOGITS
     Brooklyn
    1.36
     Vermont
    1.09
     Boulder
    1.03
    Brooklyn
    1.02
     Asheville
    0.93
     schicken
    0.93
     Seattle
    0.92
    ὐ
    0.92
     Oregon
    0.89
    Boulder
    0.88
    Activations Density 0.075%

    No Known Activations