© 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. 10-GEMMASCOPE-RES-131K
    7. 59113
    Prev
    Next
    INDEX
    Explanations

    zero out

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

    The neuron flags occurrences of the literal “zero” (in any casing) in code or 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_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
    E
    -3.38
    ↵↵
    -3.17
     hebben
    -2.83
    簠
    -2.78
    剮
    -2.77
    S
    -2.66
    腚
    -2.66
     hadden
    -2.66
     they
    -2.64
     แต่
    -2.56
    POSITIVE LOGITS
    Ꮓ
    2.91
    There
    2.88
    ACHUSET
    2.84
    趼
    2.69
    шего
    2.58
    媄
    2.50
    媖
    2.47
    犽
    2.45
    ૫
    2.45
    ſtre
    2.45
    Activations Density 0.007%

    No Known Activations