© 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. 45595
    Prev
    Next
    INDEX
    Explanations

    measuring instruments and models

    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
    概述
    -0.80
    杉
    -0.73
    kování
    -0.72
     ľudí
    -0.70
    uba
    -0.70
    ‚¬
    -0.69
    ANGA
    -0.69
    ֱ
    -0.68
    Europ
    -0.68
    дравствуйте
    -0.68
    POSITIVE LOGITS
     instruments
    1.23
     apparatus
    1.18
     instrument
    1.16
     automatic
    1.11
     Model
    1.04
     model
    1.04
     Automatic
    1.03
     instrumentos
    1.03
    Model
    1.01
    automatic
    0.98
    Activations Density 0.093%

    No Known Activations