© 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. 22-GEMMASCOPE-RES-131K
    7. 25413
    Prev
    Next
    INDEX
    Explanations

    declaratory text structures

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

    The neuron fires on code‐style tokens—things like variable and function names, macro constants, and other identifiers (often containing underscores or mixed case) rather than ordinary prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    cember
    -1.12
     české
    -1.09
     originalen
    -1.03
     különböző
    -1.00
     then
    -1.00
     soprattutto
    -0.99
     followed
    -0.98
     były
    -0.98
    kyrie
    -0.97
    ceptives
    -0.97
    POSITIVE LOGITS
    Estos
    1.19
     these
    1.16
     plut
    1.14
    Estas
    1.09
     there
    1.07
     hommage
    1.06
     attes
    1.06
     @"/
    1.05
    getchar
    1.05
     declaratory
    1.02
    Activations Density 0.014%

    No Known Activations