© 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. 118758
    Prev
    Next
    INDEX
    Explanations

    get confused or caught

    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
    waiting
    -0.93
    rassing
    -0.90
    causing
    -0.88
    indo
    -0.88
    もあり
    -0.88
    ómico
    -0.87
    experienced
    -0.85
    ileen
    -0.84
    omeness
    -0.84
     diligence
    -0.84
    POSITIVE LOGITS
     carried
    2.03
     caught
    1.51
     stuck
    1.31
     into
    1.24
     lost
    1.15
     Carried
    1.14
    carried
    1.11
     excited
    1.08
     ahead
    1.07
     upset
    1.02
    Activations Density 0.032%

    No Known Activations