© 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. 34-GEMMASCOPE-RES-131K
    7. 31087
    Prev
    Next
    INDEX
    Explanations

    to be replace

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

    This neuron fires on code‐identifier tokens that are part of generic type or method signatures—especially tokens like “byte,” “Sequence,” and related generic‐angle-bracket identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     caneca
    -1.33
     nehé
    -1.27
     escaleras
    -1.27
     lehetős
    -1.24
     tény
    -1.24
     tiroirs
    -1.23
     hossz
    -1.23
     caucho
    -1.21
     garrafa
    -1.20
     esponja
    -1.19
    POSITIVE LOGITS
     to
    6.19
    要
    2.70
    ที่จะ
    2.55
    ToBe
    2.30
    toBe
    2.30
    待
    2.08
    to
    2.08
    tobe
    2.06
     要
    1.95
     To
    1.91
    Activations Density 0.066%

    No Known Activations