© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104233
    Prev
    Next
    INDEX
    Explanations

    action verbs processing information

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

    words related to processing, analyzing, or manipulating data/information in technical or formal contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     "
    -1.23
     past
    -1.16
     ''
    -1.15
    "
    -1.11
     sees
    -1.05
     entera
    -1.05
     way
    -1.05
     ;
    -1.05
     after
    -1.02
    ),
    -1.01
    POSITIVE LOGITS
    ásica
    1.23
    ូ
    1.22
     magasiner
    1.20
    ӄ
    1.17
     moft
    1.12
     ſtre
    1.12
    பெ
    1.09
    oury
    1.07
    夔
    1.05
     Pentru
    1.04
    Activations Density 0.221%

    No Known Activations