© 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. 34253
    Prev
    Next
    INDEX
    Explanations

    captions for text

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

    This neuron triggers on instructional or editorial direction phrases—i.e. bits of text that give procedural guidance or formatting/content-management instructions.

    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
     retort
    -0.98
     batal
    -0.95
     disintegration
    -0.94
    前言
    -0.92
    运转
    -0.91
     rasg
    -0.91
     Philosop
    -0.91
     Peti
    -0.88
    Grief
    -0.88
     Klik
    -0.87
    POSITIVE LOGITS
    ètes
    1.11
     oración
    1.07
     completed
    1.05
     clients
    1.05
     customer
    1.04
    setminus
    1.03
     edit
    1.02
     altijd
    0.99
     attività
    0.96
     this
    0.96
    Activations Density 0.054%

    No Known Activations