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. 8150
    Prev
    Next
    INDEX
    Explanations

    all the

    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
     all
    -1.27
     each
    -1.26
     and
    -1.20
     a
    -1.20
     something
    -1.20
    ETHOD
    -1.16
     모두
    -1.09
     where
    -1.08
    ufes
    -1.02
     Ereignisse
    -1.02
    POSITIVE LOGITS
     of
    3.89
     the
    3.53
     navigateur
    1.21
    ñora
    1.17
     sorts
    1.16
     dagens
    1.15
     årets
    1.14
     navnet
    1.14
    возмо
    1.13
    ͝
    1.12
    Activations Density 0.040%

    No Known Activations