© 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. 63078
    Prev
    Next
    INDEX
    Explanations

    layout and constraints

    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
    誹
    -0.92
    cartera
    -0.87
    藤原
    -0.84
     architekt
    -0.82
     смесь
    -0.82
    ଶ
    -0.82
    leos
    -0.81
    
    -0.80
     knob
    -0.80
    预约
    -0.79
    POSITIVE LOGITS
    マシ
    0.82
    <=
    0.82
    依
    0.81
    Margin
    0.79
    setVerticalGroup
    0.79
     yog
    0.79
     sudoku
    0.79
    >=
    0.79
     iguales
    0.78
     margins
    0.76
    Activations Density 0.004%

    No Known Activations