© 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. 104667
    Prev
    Next
    INDEX
    Explanations

    making smaller

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

    The neuron is triggered by numeric quantities and related comparative terms (numbers, measures, “more,” “than,” etc.).

    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
     Bilingual
    -0.84
     mojo
    -0.79
     verfügt
    -0.79
     Ooh
    -0.79
    ätter
    -0.77
     grooved
    -0.77
     POOR
    -0.75
     Buhari
    -0.74
     unarmed
    -0.74
     capacité
    -0.73
    POSITIVE LOGITS
    FindBy
    0.82
     począ
    0.77
     подразде
    0.76
     каба
    0.75
     impurities
    0.73
    PKCS
    0.73
    ToDelete
    0.72
    Nonnull
    0.72
     медици
    0.72
    입니다
    0.72
    Activations Density 0.069%

    No Known Activations