© 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. 49075
    Prev
    Next
    INDEX
    Explanations

    lengths, shapes, and dimensions

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

    This neuron responds to step-by-step DIY/procedural instructions, especially imperative action verbs (measure, cut, glue, assemble, etc.) and related language.

    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
    tenths
    -1.17
    ְּ
    -1.16
     maal
    -1.12
     flotte
    -1.11
     caricatura
    -1.11
    }\]
    -1.06
    ִּ
    -1.05
    ronym
    -1.05
     què
    -1.04
     períodos
    -1.03
    POSITIVE LOGITS
     you
    1.09
     roughly
    1.08
     your
    1.05
     entstehen
    1.04
     aproximadamente
    1.02
     tutorial
    0.97
     approximately
    0.97
     proyectos
    0.97
     smaller
    0.95
     pieces
    0.94
    Activations Density 0.039%

    No Known Activations