© 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. 117322
    Prev
    Next
    INDEX
    Explanations

    timestamps followed by colon

    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
     Substanz
    -0.97
     these
    -0.85
     encaps
    -0.80
    inetto
    -0.77
     anticipated
    -0.76
    さっそく
    -0.75
     wider
    -0.75
     Probleme
    -0.74
     Kommun
    -0.74
     said
    -0.74
    POSITIVE LOGITS
    pm
    1.01
    PM
    0.94
     médicaux
    0.91
     rembour
    0.91
     THIR
    0.88
    AM
    0.88
    Cristo
    0.86
     impresa
    0.85
    hacer
    0.85
    らう
    0.85
    Activations Density 0.035%

    No Known Activations