© 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. 70532
    Prev
    Next
    INDEX
    Explanations

    place names and institutions

    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
     spesielt
    -1.58
    ↵↵
    -1.51
     personalizadas
    -1.48
     cristo
    -1.45
     escaleras
    -1.45
     educativas
    -1.45
     gratuitas
    -1.44
     málaga
    -1.44
     vasco
    -1.43
     iniqu
    -1.43
    POSITIVE LOGITS
     dijo
    1.66
    (!__
    1.55
    <td>
    1.55
    ć
    1.53
    KommentareTeilen
    1.53
     $\
    1.52
     ),
    1.52
    ₤
    1.49
     to
    1.47
     exist
    1.44
    Activations Density 0.992%

    No Known Activations