Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 365
    Prev
    Next
    INDEX
    Explanations

    names like Ahmad, Allah, God

    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
     at
    -2.20
     has
    -2.06
     through
    -1.80
     out
    -1.74
     Also
    -1.63
     to
    -1.59
     all
    -1.55
     an
    -1.54
     from
    -1.52
     unparalleled
    -1.51
    POSITIVE LOGITS
     haupts
    1.67
     Schluß
    1.67
     vorigen
    1.63
     wonderful
    1.58
     bestätigen
    1.54
     nunmehr
    1.50
    2
    1.49
     Gegenteil
    1.48
     zustand
    1.48
     nachfol
    1.48
    Activations Density 0.003%

    No Known Activations