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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11602
    Prev
    Next
    INDEX
    Explanations

    but signals a contrast

    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
     thereunder
    -0.89
    𝚣
    -0.85
    핌
    -0.85
     nötig
    -0.84
    odotus
    -0.83
    ouncements
    -0.83
     スニーカー
    -0.82
    Twitch
    -0.81
     obiettivo
    -0.81
    paa
    -0.80
    POSITIVE LOGITS
     unable
    1.11
     because
    1.06
     cannot
    1.05
     powerless
    1.00
     Unable
    0.94
    Unable
    0.93
     still
    0.93
     until
    0.92
     faute
    0.89
     so
    0.84
    Activations Density 0.039%

    No Known Activations