© 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. 78092
    Prev
    Next
    INDEX
    Explanations

    window/form attributes

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

    The neuron fires on code‐level identifiers and element/property names (e.g. HTML tags, class or enum names, and code/markup attribute names).

    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
    FloatField
    -0.98
     manifestazione
    -0.92
     WALTZ
    -0.88
    ួ
    -0.87
     artykuł
    -0.85
     COUNTRIES
    -0.84
    livejournal
    -0.84
     descubierto
    -0.82
     instrucción
    -0.82
     Databases
    -0.81
    POSITIVE LOGITS
     ((
    1.09
     (
    1.02
     An
    0.89
     Anchor
    0.88
    ((
    0.86
     anchor
    0.85
     None
    0.84
     System
    0.84
     A
    0.80
     Dos
    0.77
    Activations Density 0.001%

    No Known Activations