© 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. 22-GEMMASCOPE-RES-131K
    7. 11408
    Prev
    Next
    INDEX
    Explanations

    specification, emission, production, antigen

    np_acts-logits-general · gemini-2.5-flash-lite

    technical terms in academic or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     achieve
    -0.90
     focusing
    -0.90
     Both
    -0.89
     on
    -0.86
     provide
    -0.86
     that
    -0.85
     when
    -0.85
     get
    -0.84
     as
    -0.83
     éves
    -0.83
    POSITIVE LOGITS
     paraître
    1.07
     varier
    0.93
     manquer
    0.90
     apparaître
    0.90
    EVEN
    0.87
     oublier
    0.84
     tava
    0.82
     portu
    0.82
    somewhat
    0.82
    otherwise
    0.82
    Activations Density 0.409%

    No Known Activations