© 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. 1079
    Prev
    Next
    INDEX
    Explanations

    geometric features and structures

    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
    noted
    -0.84
    idar
    -0.84
    sphere
    -0.82
     mengucap
    -0.79
    endpush
    -0.79
    isDebugEnabled
    -0.78
    axios
    -0.78
    ellee
    -0.77
    oluble
    -0.77
    ẹn
    -0.76
    POSITIVE LOGITS
     undercut
    1.05
     trenches
    1.04
     feature
    1.03
     structures
    0.98
     pillars
    0.97
     Structures
    0.97
     patterned
    0.94
     meander
    0.93
     islands
    0.92
     sacrificial
    0.92
    Activations Density 0.251%

    No Known Activations