© 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. 34-GEMMASCOPE-RES-131K
    7. 48584
    Prev
    Next
    INDEX
    Explanations

    roll bars and phrases

    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
     mutable
    -0.76
    𝚑
    -0.72
    CLICK
    -0.70
     jing
    -0.70
    췄
    -0.69
     Apa
    -0.68
    KEYWORDS
    -0.67
    Click
    -0.67
    IBase
    -0.67
     մ
    -0.67
    POSITIVE LOGITS
     cage
    1.42
     roll
    1.27
     cages
    1.14
     bars
    1.11
     protection
    1.11
     Protection
    1.08
     Protective
    1.06
     tubular
    1.04
     protect
    1.03
     ROLL
    1.00
    Activations Density 0.024%

    No Known Activations