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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7913
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    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
     and
    -2.06
     for
    -1.65
     of
    -1.59
     or
    -1.40
     on
    -1.38
     to
    -1.33
     as
    -1.29
     at
    -1.21
     which
    -1.18
     until
    -1.16
    POSITIVE LOGITS
     refroid
    1.24
     précip
    1.16
     ネック
    1.16
     ajouter
    1.15
    Adds
    1.11
    werke
    1.10
     ARISING
    1.09
     redé
    1.09
     empêcher
    1.09
     contribuer
    1.09
    Activations Density 0.017%

    No Known Activations