© 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. 34-GEMMASCOPE-RES-131K
    7. 92124
    Prev
    Next
    INDEX
    Explanations

    code parsing and string manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     intval
    -0.94
    =$((
    -0.82
     piemē
    -0.79
     paliwa
    -0.79
     echten
    -0.79
    nappropriate
    -0.75
     '/';
    -0.75
     Überblick
    -0.75
    頃に
    -0.75
    য়
    -0.74
    POSITIVE LOGITS
     Escape
    1.24
    escape
    1.24
     escape
    1.10
    Escape
    1.07
     Uri
    1.05
     escapes
    0.99
     medy
    0.98
    strip
    0.96
    Strip
    0.96
     Trim
    0.96
    Activations Density 0.010%

    No Known Activations