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-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 543
    Prev
    Next
    INDEX
    Explanations

    words that indicate lists or enumerations

    np_acts-logits-general · gemini-2.5-flash-lite

    decline of activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    0.64
     myself
    0.64
    A
    0.63
     an
    0.61
     in
    0.59
     A
    0.59
     Myself
    0.59
     Vintage
    0.57
    I
    0.57
    ждый
    0.55
    POSITIVE LOGITS
     hypothalamus
    0.59
     গ্রেফতার
    0.57
    rrbracket
    0.56
     کشور
    0.55
    ផ្ល
    0.55
     coûts
    0.55
     대응
    0.55
     países
    0.54
     బీజేపీ
    0.54
     órgãos
    0.54
    Activations Density 0.000%

    No Known Activations