© 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. 7980
    Prev
    Next
    INDEX
    Explanations

    tram, trolley, streetcar, light rail

    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
     considération
    -2.59
    Ἢ
    -2.28
     în
    -2.28
     Gewähr
    -2.25
    sandalia
    -2.23
    
    -2.23
     However
    -2.19
    ࿆
    -2.16
     estadía
    -2.16
     Voraussetzung
    -2.14
    POSITIVE LOGITS
     cientí
    2.11
     prácticamente
    2.05
    at
    2.05
    ністю
    2.02
    e
    1.98
    —
    1.98
    
    1.95
    '''
    1.94
     arv
    1.94
    {
    1.93
    Activations Density 0.003%

    No Known Activations