Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 154
    Prev
    Next
    INDEX
    Explanations

    no fees, charges, or waiting

    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
     without
    -1.66
     Without
    -1.23
     fără
    -1.13
     ohne
    -1.09
     Especially
    -1.09
     piuttosto
    -1.06
     WITHOUT
    -1.06
    Without
    -1.05
     especially
    -1.02
     tanpa
    -1.00
    POSITIVE LOGITS
     nor
    2.16
     unlike
    1.74
     whatsoever
    1.71
    unlike
    1.65
    nor
    1.45
    而是
    1.30
     or
    1.30
     Unlike
    1.23
    ใด
    1.20
     dzięki
    1.19
    Activations Density 0.074%

    No Known Activations