© 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. 57957
    Prev
    Next
    INDEX
    Explanations

    any later version

    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
    橱
    -0.71
     Nand
    -0.70
    breeding
    -0.67
     Salas
    -0.65
    個室
    -0.64
     Holdings
    -0.63
     Coalition
    -0.62
    ウォーター
    -0.62
     Meaning
    -0.62
     oy
    -0.62
    POSITIVE LOGITS
     gpu
    0.70
     style
    0.68
    лав
    0.66
    舰
    0.65
    żdż
    0.65
    Floral
    0.65
     opcion
    0.65
     препратки
    0.64
    ongoose
    0.63
     snake
    0.63
    Activations Density 0.065%

    No Known Activations