© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15788
    Prev
    Next
    INDEX
    Explanations

    frequency of events

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

    The neuron activates on numerical tokens, identifying numbers (counts, years, quantities) in the text.

    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
     that
    -1.63
     and
    -1.41
     including
    -1.28
     many
    -1.24
     while
    -1.20
     what
    -1.20
     even
    -1.20
     heutigen
    -1.18
     pay
    -1.14
     pierwsze
    -1.12
    POSITIVE LOGITS
     annually
    1.49
     varje
    1.30
     inaugura
    1.23
    yearly
    1.20
    每年
    1.20
     espé
    1.19
     englisch
    1.17
    綰
    1.16
    whenever
    1.16
     anual
    1.15
    Activations Density 0.037%

    No Known Activations