© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1237
    Prev
    Next
    INDEX
    Explanations

    attributes, sequences, and states

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

    technical descriptions of experimental stimuli, attributes, or features in cognitive/perceptual research contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -2.13
     pittores
    -1.44
     then
    -1.39
     now
    -1.39
     jaun
    -1.36
     eif
    -1.36
    ·
    -1.34
    erobic
    -1.34
     bret
    -1.31
     艺术
    -1.30
    POSITIVE LOGITS
     or
    1.82
     first
    1.62
     cár
    1.57
     at
    1.55
     during
    1.49
     could
    1.46
     comienzos
    1.45
    ppuden
    1.42
     other
    1.40
    انظر
    1.39
    Activations Density 0.513%

    No Known Activations