© 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. 10-GEMMASCOPE-RES-131K
    7. 101474
    Prev
    Next
    INDEX
    Explanations

    statement or release

    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_10/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
     многих
    -1.46
     many
    -1.30
    Many
    -1.30
     Eigentü
    -1.28
    ēr
    -1.27
     عندما
    -1.27
    各种
    -1.25
     manchmal
    -1.20
    有很多
    -1.19
     muchísimo
    -1.16
    POSITIVE LOGITS
     its
    1.36
     as
    1.26
    typer
    1.13
     Harvesting
    1.09
     again
    1.09
     he
    1.09
    莼
    1.02
    loaders
    1.02
    ępo
    1.01
    夯
    1.01
    Activations Density 0.025%

    No Known Activations