© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99073
    Prev
    Next
    INDEX
    Explanations

    curve and its fitting

    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
     utilizzare
    -0.99
    柔らかい
    -0.98
    ㈣
    -0.97
    都沒
    -0.96
    ⟣
    -0.91
    
    -0.89
     koi
    -0.89
    medriver
    -0.89
    也沒
    -0.88
    verläs
    -0.87
    POSITIVE LOGITS
    ball
    1.66
     curves
    1.37
     curve
    1.29
    balls
    1.25
    curve
    1.23
     Curve
    1.22
     Cur
    1.11
    Curve
    1.03
     Curves
    1.02
    Cur
    1.02
    Activations Density 0.007%

    No Known Activations