© 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. 34-GEMMASCOPE-RES-131K
    7. 119047
    Prev
    Next
    INDEX
    Explanations

    words starting with tob

    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_34/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
    counting
    -0.84
    颔
    -0.81
    erad
    -0.79
    規則
    -0.78
    nows
    -0.78
     كتب
    -0.75
     COUNT
    -0.74
    嗑
    -0.74
    くちゃ
    -0.74
    ūros
    -0.73
    POSITIVE LOGITS
     Tob
    1.05
    Tob
    0.93
    താ
    0.87
     Toby
    0.81
     tob
    0.81
    Toby
    0.74
    Δείτε
    0.69
     embarrassed
    0.69
     often
    0.66
     essential
    0.66
    Activations Density 0.015%

    No Known Activations