© 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. 10-GEMMASCOPE-RES-131K
    7. 20094
    Prev
    Next
    INDEX
    Explanations

    words starting with Ne

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

    The neuron fires on very short, two‐character tokens (e.g. “Ne”, “yu”, “يه”).

    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
    AN
    -2.33
    箧
    -2.23
    ły
    -2.22
    r
    -2.20
    ENT
    -2.20
    does
    -2.17
    躂
    -2.17
    炻
    -2.16
    也会
    -2.14
    .";
    -2.14
    POSITIVE LOGITS
    缐
    2.09
     brought
    2.02
    に使
    1.98
    Despite
    1.98
    getSystemService
    1.98
    beqa
    1.95
    Those
    1.95
    borderSide
    1.95
     displayed
    1.91
    閻
    1.91
    Activations Density 0.001%

    No Known Activations