© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82502
    Prev
    Next
    INDEX
    Explanations

    confirming or updating state

    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
     by
    -1.32
     with
    -1.02
     to
    -0.98
     from
    -0.97
     should
    -0.94
     during
    -0.91
     in
    -0.89
    These
    -0.88
     for
    -0.86
     on
    -0.85
    POSITIVE LOGITS
    τσ
    0.92
    WING
    0.92
    蛳
    0.91
    셍
    0.90
     cohesion
    0.87
     coke
    0.86
     adecuados
    0.86
    ьера
    0.85
    huang
    0.84
    krä
    0.84
    Activations Density 0.021%

    No Known Activations