© 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. 76727
    Prev
    Next
    INDEX
    Explanations

    record highs and lows

    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
    襖
    -1.04
     calorías
    -0.94
    当我
    -0.94
    髂
    -0.91
    Ahhhh
    -0.90
     embalaje
    -0.88
     emisiones
    -0.88
     cantidades
    -0.85
     которы
    -0.85
     CURIAM
    -0.85
    POSITIVE LOGITS
     ever
    2.16
     any
    2.00
     recorded
    1.82
     anyone
    1.59
     since
    1.56
     jamais
    1.41
     in
    1.38
     such
    1.25
     anybody
    1.20
     Recorded
    1.20
    Activations Density 0.046%

    No Known Activations