© 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. 120028
    Prev
    Next
    INDEX
    Explanations

    desire or longing

    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
     decoradas
    -2.56
     pintadas
    -2.45
    ?’
    -2.42
     marcadas
    -2.33
     />";
    -2.31
    Więcej
    -2.31
     músculos
    -2.30
     consideradas
    -2.30
     preciosas
    -2.30
    !’
    -2.25
    POSITIVE LOGITS
     
    2.84
    ’
    2.53
    "
    2.47
    $
    2.45
     '
    2.44
    an
    2.39
    1
    2.27
    that
    2.27
    ↵↵
    2.23
    /
    2.19
    Activations Density 0.003%

    No Known Activations