© 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. 30291
    Prev
    Next
    INDEX
    Explanations

    authorization and coding comments

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

    The neuron is firing on code‐style tokens—especially punctuation used in syntax (e.g. “{”, “<”, “>”) and all-caps identifiers or constants (strings of uppercase letters and underscores).

    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
     your
    -0.82
     equal
    -0.73
    Fuck
    -0.72
     so
    -0.72
     krav
    -0.70
     Scientist
    -0.70
     industrial
    -0.69
    organiser
    -0.69
     voile
    -0.69
    竞技
    -0.69
    POSITIVE LOGITS
     episódios
    0.97
    襦
    0.97
    òi
    0.93
    ătoare
    0.92
    ddha
    0.91
    Lieferumfang
    0.88
    undos
    0.88
    tioner
    0.88
    LinkId
    0.83
    ppone
    0.82
    Activations Density 0.005%

    No Known Activations