© 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. 39944
    Prev
    Next
    INDEX
    Explanations

    file extensions like jpg, tif, pdf, java

    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
    хим
    -1.36
     originalen
    -1.25
    rschein
    -1.21
     údaje
    -1.20
    indelijk
    -1.17
     Água
    -1.17
     Spisak
    -1.16
    捽
    -1.16
     TECHNI
    -1.16
     mittels
    -1.16
    POSITIVE LOGITS
    ?
    1.55
    :
    1.32
    !
    1.29
    ...
    1.22
    ",
    1.21
    .,
    1.20
     CO
    1.16
    "
    1.16
    肜
    1.16
    .='
    1.15
    Activations Density 0.064%

    No Known Activations