© 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. 49496
    Prev
    Next
    INDEX
    Explanations

    pixel or pixels and their properties

    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
    ↵↵
    -0.93
     vieles
    -0.90
     电脑
    -0.89
     begleiten
    -0.86
     pilates
    -0.85
     faisant
    -0.85
     wüns
    -0.84
    骋
    -0.84
     they
    -0.82
     oč
    -0.81
    POSITIVE LOGITS
    ated
    1.66
     perfect
    1.23
    mator
    1.13
    perfect
    1.10
    dziew
    1.03
     shader
    1.01
    Perfect
    1.00
    PerSecond
    0.97
    ATED
    0.97
     perfekt
    0.94
    Activations Density 0.008%

    No Known Activations