© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113497
    Prev
    Next
    INDEX
    Explanations

    code file paths and crypto

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

    forward slashes that appear in file paths, URLs, or code syntax.

    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
     its
    -1.54
    它是
    -1.42
     его
    -1.42
     одному
    -1.33
     sirva
    -1.30
    Its
    -1.29
    他の
    -1.27
    ="
    -1.27
     Its
    -1.24
     Про
    -1.23
    POSITIVE LOGITS
     including
    1.36
     dreamstime
    1.34
     Ministero
    1.33
    czego
    1.31
     trofeo
    1.29
     navide
    1.27
     面包
    1.27
     Krzysz
    1.26
     Galería
    1.23
     veicolo
    1.23
    Activations Density 0.157%

    No Known Activations