© 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. 31457
    Prev
    Next
    INDEX
    Explanations

    First Evidence

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

    This neuron detects isolated capitalized words that serve as titles, headings, or proper 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
     reizen
    -1.20
     wensen
    -1.18
     norvég
    -1.10
    走吧
    -1.09
     guste
    -1.06
     akku
    -1.05
     Majefty
    -1.04
    棪
    -1.04
     土産
    -1.03
     WALT
    -1.02
    POSITIVE LOGITS
     Y
    1.30
     E
    1.23
     Z
    1.21
     M
    1.16
     A
    1.16
    :
    1.14
     G
    1.13
     y
    1.12
     =
    1.11
     K
    1.11
    Activations Density 0.000%

    No Known Activations