© 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. 31378
    Prev
    Next
    INDEX
    Explanations

    in followed by location or context

    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
    獅
    -0.95
    ård
    -0.90
    tieth
    -0.90
    や
    -0.88
    も
    -0.88
    ha
    -0.86
    cising
    -0.85
    kowitz
    -0.84
    dé
    -0.84
     wyboru
    -0.84
    POSITIVE LOGITS
     llvm
    0.87
     few
    0.86
     Jut
    0.84
     quen
    0.82
     Quel
    0.81
    んですか
    0.81
     "--
    0.81
     trun
    0.81
     Ters
    0.81
    Pham
    0.80
    Activations Density 0.004%

    No Known Activations