© 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. 22-GEMMASCOPE-RES-131K
    7. 38682
    Prev
    Next
    INDEX
    Explanations

    scoring goals

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

    The main thing this neuron does is find numeric tokens (counts, measurements, and decimal figures).

    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
     HasFactory
    -1.26
    ască
    -1.14
    rophes
    -1.09
     چیه
    -1.09
    BASEPATH
    -1.09
    phère
    -1.06
    lahraga
    -1.05
     anstatt
    -1.04
     instead
    -1.02
    dicionado
    -1.01
    POSITIVE LOGITS
     in
    1.56
     contribution
    1.25
    дное
    1.20
     goals
    1.11
     каждо
    1.06
     contributed
    1.02
     sichere
    1.01
    ✆
    1.00
     against
    1.00
    diera
    1.00
    Activations Density 0.015%

    No Known Activations