© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56816
    Prev
    Next
    INDEX
    Explanations

    frame or frames

    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
    Negative Logits
    Rede
    -0.79
     Krum
    -0.77
     concre
    -0.76
     Breaks
    -0.74
     照
    -0.72
    vgl
    -0.69
    тельного
    -0.69
    tamina
    -0.68
    TMR
    -0.65
     Lübeck
    -0.64
    POSITIVE LOGITS
     frames
    1.10
     frame
    1.02
     Frame
    1.00
    Frame
    0.97
     Frames
    0.95
    Frames
    0.93
    frame
    0.91
    帧
    0.91
     WINDOW
    0.89
     FRAME
    0.86
    Activations Density 0.008%

    No Known Activations