© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118883
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
     one
    -1.09
    ッキング
    -1.04
     for
    -1.01
     by
    -0.97
    看看
    -0.95
    묻
    -0.91
     mostly
    -0.91
    这里的
    -0.90
     you
    -0.89
     probably
    -0.88
    POSITIVE LOGITS
     while
    1.37
     given
    1.34
     due
    1.33
    while
    1.29
     based
    1.28
     we
    1.28
    given
    1.27
    Based
    1.23
     our
    1.22
    While
    1.20
    Activations Density 0.029%

    No Known Activations