© 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. 34-GEMMASCOPE-RES-131K
    7. 64361
    Prev
    Next
    INDEX
    Explanations

    URLs and code identifiers

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

    The neuron is keyed to code‐style identifiers and acronyms (e.g. CamelCase names and all-caps tokens) rather than ordinary words.

    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
     will
    -0.82
     until
    -0.71
     Librarians
    -0.71
    will
    -0.69
     convey
    -0.68
    Convey
    -0.67
    Will
    -0.66
    دى
    -0.66
     Convey
    -0.66
     ער
    -0.66
    POSITIVE LOGITS
     produkcji
    0.75
    yeti
    0.74
     야
    0.71
    zach
    0.68
     blusa
    0.68
     clazz
    0.68
     février
    0.66
    thumbsup
    0.66
     matematika
    0.66
     fré
    0.66
    Activations Density 0.061%

    No Known Activations