© 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. 99037
    Prev
    Next
    INDEX
    Explanations

    spatial distributions and patterns

    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
     BoxDecoration
    -0.98
     SPACE
    -0.91
     både
    -0.90
    space
    -0.88
    цію
    -0.87
    筏
    -0.87
     difficiles
    -0.85
     berdua
    -0.85
    appointments
    -0.85
    瘻
    -0.84
    POSITIVE LOGITS
    temporal
    1.05
    ized
    1.03
     extent
    0.96
    ty
    0.94
    What
    0.91
     distribution
    0.90
    izing
    0.84
     endless
    0.83
     proximity
    0.82
     continuous
    0.81
    Activations Density 0.025%

    No Known Activations