© 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. 118872
    Prev
    Next
    INDEX
    Explanations

    Submitted dates

    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
     Pagination
    -0.73
     hipo
    -0.73
    Orb
    -0.71
     ITIS
    -0.71
    erv
    -0.70
    fleet
    -0.69
     Гла
    -0.67
    ♣
    -0.67
     Fleet
    -0.67
    аль
    -0.66
    POSITIVE LOGITS
    င
    0.69
     counsellor
    0.69
    :"",
    0.68
    ჰ
    0.68
     modded
    0.68
     contesting
    0.68
     homeward
    0.66
     publicada
    0.66
     herbicide
    0.65
     motori
    0.65
    Activations Density 0.062%

    No Known Activations