© 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. 77766
    Prev
    Next
    INDEX
    Explanations

    default values

    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
    iseite
    -1.05
     někter
    -0.97
    一方面
    -0.95
    ídio
    -0.95
     móg
    -0.95
     väh
    -0.95
     estén
    -0.93
     niektor
    -0.93
     mohli
    -0.93
     comenzaron
    -0.92
    POSITIVE LOGITS
     defaults
    1.50
     will
    1.44
     default
    1.38
    默认为
    1.25
    default
    1.19
    默认
    1.18
    Defaults
    1.16
    defaults
    1.16
     استفاده
    1.13
    Default
    1.11
    Activations Density 0.058%

    No Known Activations