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. 8762
    Prev
    Next
    INDEX
    Explanations

    hex codes and includes

    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
    Even
    -1.47
    źródło
    -1.40
    Beskrivelse
    -1.28
    Shortly
    -1.27
    Having
    -1.25
    にほんブログ村
    -1.24
    Several
    -1.23
    Through
    -1.23
    Although
    -1.16
    ※※
    -1.16
    POSITIVE LOGITS
    [(
    1.02
    ce
    0.98
    BA
    0.98
     e
    0.97
     ridiculously
    0.96
     eas
    0.96
     Ad
    0.95
    (
    0.94
     D
    0.93
    0
    0.93
    Activations Density 0.001%

    No Known Activations