© 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. 118650
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    ↵
    -1.30
     such
    -1.23
    ==""){
    -1.07
    小说
    -1.06
     like
    -1.06
     constant
    -1.02
     تعدى
    -1.01
     likes
    -0.95
    <td>
    -0.95
    散文
    -0.94
    POSITIVE LOGITS
     ২০১
    1.66
     २०
    1.52
     תש
    1.26
     vuonna
    1.23
     ২০
    1.16
    ğum
    1.15
     trattano
    1.14
     YYYY
    1.10
     pandémie
    1.08
    ícia
    1.03
    Activations Density 0.079%

    No Known Activations