© 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. 10-GEMMASCOPE-RES-131K
    7. 48394
    Prev
    Next
    INDEX
    Explanations

    all or at least

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

    This neuron activates on numeric or quantitative expressions—words and phrases that specify amounts, thresholds, or numeric conditions (e.g., “at least,” “minimum of,” specific numbers, and similar quantifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ohne
    -1.41
     SUSTAIN
    -1.18
    theros
    -1.16
    משך
    -1.16
     then
    -1.16
    BIL
    -1.15
     obvio
    -1.14
    εβ
    -1.13
    GRUPO
    -1.13
    část
    -1.12
    POSITIVE LOGITS
     their
    1.99
     these
    1.59
     this
    1.42
     our
    1.33
     his
    1.33
    adec
    1.21
     new
    1.20
     including
    1.16
     except
    1.14
     from
    1.12
    Activations Density 0.338%

    No Known Activations