© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106575
    Prev
    Next
    INDEX
    Explanations

    introducing academic methods

    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
     ۱۱
    -0.94
     বল
    -0.93
     eenige
    -0.92
    𝓕
    -0.92
     ۷
    -0.92
    向けの
    -0.91
    tierten
    -0.87
    ῴ
    -0.87
     ২
    -0.86
     nowego
    -0.86
    POSITIVE LOGITS
     proposed
    2.88
     developed
    2.20
     suggested
    2.09
     by
    2.06
    proposed
    1.96
     due
    1.95
    Proposed
    1.94
     Proposed
    1.88
     introduced
    1.84
     of
    1.74
    Activations Density 0.134%

    No Known Activations