© 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. 12288
    Prev
    Next
    INDEX
    Explanations

    immediately, now, already

    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
    Dopo
    -1.00
    Werdegang
    -0.83
    cijos
    -0.82
    idings
    -0.81
     finalement
    -0.81
    Blockly
    -0.80
    Depois
    -0.79
    猛地
    -0.78
     später
    -0.77
    leistungen
    -0.77
    POSITIVE LOGITS
     already
    2.84
     immediately
    2.67
     immediate
    2.31
    Already
    2.02
     уже
    1.97
    immediate
    1.97
     Already
    1.95
    already
    1.91
     już
    1.86
     вже
    1.82
    Activations Density 0.083%

    No Known Activations