© 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. 10-GEMMASCOPE-RES-131K
    7. 84891
    Prev
    Next
    INDEX
    Explanations

    shelter

    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
    鰨
    -2.66
    ad
    -2.59
    en
    -2.58
    餿
    -2.48
    end
    -2.41
    屺
    -2.39
    èdent
    -2.25
     characterizes
    -2.16
    седа
    -2.16
    umbling
    -2.16
    POSITIVE LOGITS
    \
    3.16
    ;
    2.84
     otras
    2.80
    ).
    2.73
    ))
    2.38
     outras
    2.33
    It
    2.28
    鄠
    2.23
     специаль
    2.22
    (“
    2.22
    Activations Density 0.003%

    No Known Activations