© 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. 48450
    Prev
    Next
    INDEX
    Explanations

    frame structures

    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
    ceptives
    -0.98
    융
    -0.77
    umpang
    -0.69
    iego
    -0.68
     فت
    -0.66
    dende
    -0.66
    itaries
    -0.66
    upyter
    -0.64
     Stones
    -0.63
    앞
    -0.63
    POSITIVE LOGITS
     frame
    3.55
     framework
    3.41
     frames
    3.06
    frame
    2.73
    框架
    2.70
     Frame
    2.66
    Frame
    2.66
    framework
    2.64
    FRAME
    2.63
     frameworks
    2.59
    Activations Density 0.117%

    No Known Activations