© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40383
    Prev
    Next
    INDEX
    Explanations

    // Copyright, Hands-on, Mapping, Burren

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

    This neuron fires on numeric and measurement tokens (counts, units, and other quantitative details) typically found in listing‐style/specification contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     разных
    -1.72
     teuer
    -1.64
     różnych
    -1.62
     bekannten
    -1.53
     innych
    -1.49
     моего
    -1.48
     choroby
    -1.46
     Що
    -1.45
     específicos
    -1.45
     distintos
    -1.45
    POSITIVE LOGITS
     your
    2.19
     you
    1.89
     this
    1.66
     with
    1.47
     of
    1.45
     also
    1.42
     nesse
    1.41
     an
    1.35
     all
    1.31
     just
    1.31
    Activations Density 0.004%

    No Known Activations