© 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. 91557
    Prev
    Next
    INDEX
    Explanations

    gap and clearance between things

    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
     kompleks
    -0.72
     át
    -0.71
     Hurst
    -0.71
     strtok
    -0.70
    未知
    -0.70
     pembunuhan
    -0.70
    GMT
    -0.70
     mutations
    -0.69
    ยาว
    -0.69
    LENGTH
    -0.68
    POSITIVE LOGITS
     gap
    4.69
     gaps
    3.91
    gap
    3.64
    Gap
    3.64
     Gap
    3.52
    gaps
    2.89
     Gaps
    2.83
     GAP
    2.66
    GAP
    2.64
     space
    2.59
    Activations Density 0.135%

    No Known Activations