© 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. 12359
    Prev
    Next
    INDEX
    Explanations

    forms of knowing

    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_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
     kejadian
    -0.95
    arschu
    -0.93
    Život
    -0.93
    ومه
    -0.92
    denver
    -0.92
    arsi
    -0.89
     stutter
    -0.88
     still
    -0.88
     žele
    -0.85
     then
    -0.85
    POSITIVE LOGITS
     that
    1.34
     know
    1.23
     knows
    1.22
    mdash
    1.02
    ляют
    0.96
     PICK
    0.96
     but
    0.95
    这些
    0.95
    Δ
    0.94
     knew
    0.93
    Activations Density 0.035%

    No Known Activations