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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40540
    Prev
    Next
    INDEX
    Explanations

    enantiomers of alkylarylcarbinols

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

    specialized terminology, particularly scientific and technical terms.

    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_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
     with
    -2.59
     where
    -2.52
     that
    -2.48
     who
    -2.23
     what
    -2.13
     only
    -1.95
     like
    -1.83
    ),
    -1.66
     (
    -1.66
     whose
    -1.63
    POSITIVE LOGITS
    踅
    2.23
     provincie
    1.70
    ulation
    1.65
     camion
    1.63
     soixante
    1.63
     officier
    1.61
     ſeveral
    1.59
    ㈲
    1.59
     ſever
    1.59
    ཥ
    1.59
    Activations Density 0.134%

    No Known Activations