© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41849
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    0
    -2.56
     "
    -1.83
    (\
    -1.79
    "--
    -1.78
    in
    -1.76
     freaking
    -1.66
    médi
    -1.63
    <th>
    -1.63
     использовании
    -1.62
    tmp
    -1.60
    POSITIVE LOGITS
    selbe
    1.78
     Consequently
    1.62
    FFIX
    1.61
    Such
    1.58
     Such
    1.50
    ization
    1.50
     preparo
    1.47
     zentrale
    1.45
    Highly
    1.44
    ANTES
    1.38
    Activations Density 0.025%

    No Known Activations