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. 7865
    Prev
    Next
    INDEX
    Explanations

    French vocabulary

    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
     such
    -1.11
     what
    -1.04
     this
    -1.02
     after
    -1.02
     on
    -1.02
     other
    -0.99
     very
    -0.98
     many
    -0.96
     What
    -0.93
     these
    -0.93
    POSITIVE LOGITS
     juſ
    1.12
     metodi
    1.10
     frança
    1.10
     douane
    1.04
     chirurgie
    1.02
     méda
    0.98
     opérateur
    0.97
    クリル
    0.96
     ܘ
    0.96
     maksi
    0.96
    Activations Density 0.006%

    No Known Activations