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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110133
    Prev
    Next
    INDEX
    Explanations

    URL fragments and code identifiers

    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
    dfunding
    -0.68
     изда
    -0.65
    encji
    -0.65
     LPC
    -0.64
     gothic
    -0.63
    ネ
    -0.63
    Сред
    -0.63
    ҙ
    -0.63
     русском
    -0.62
    lhs
    -0.61
    POSITIVE LOGITS
    ₲
    0.68
    laması
    0.64
     weißem
    0.64
    ußt
    0.64
     Unters
    0.64
    ươi
    0.63
    一位
    0.63
     साथ
    0.63
     satisfaction
    0.62
    튠
    0.62
    Activations Density 0.042%

    No Known Activations