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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12350
    Prev
    Next
    INDEX
    Explanations

    used after 'who'

    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_22/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
     necessariamente
    -1.37
     radioButton
    -1.33
     entonces
    -1.32
     Reſ
    -1.29
     eingeladen
    -1.29
     quoc
    -1.27
     zood
    -1.27
    cshtml
    -1.27
     frança
    -1.26
    introdu
    -1.26
    POSITIVE LOGITS
     also
    2.20
     ebenfalls
    1.80
     is
    1.74
     has
    1.63
    อีก
    1.58
    Также
    1.55
     также
    1.51
    これも
    1.50
    こちらも
    1.48
     only
    1.42
    Activations Density 0.016%

    No Known Activations