© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119421
    Prev
    Next
    INDEX
    Explanations

    code structure and commands

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

    technical terms in programming and software documentation, particularly related to filters, passes, constraints, and system components.

    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
     was
    -1.58
     despite
    -1.47
     egenskaper
    -1.40
     illustrationer
    -1.34
    cún
    -1.33
     behandling
    -1.23
     one
    -1.21
     annons
    -1.20
    Despite
    -1.17
    çou
    -1.16
    POSITIVE LOGITS
     you
    1.63
     Obtén
    1.60
     such
    1.58
     also
    1.50
     estos
    1.46
     Selecciona
    1.45
    轳
    1.44
     donc
    1.43
     Fácil
    1.42
     también
    1.39
    Activations Density 0.166%

    No Known Activations