© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110448
    Prev
    Next
    INDEX
    Explanations

    making provision of or for

    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
     tracción
    -1.30
     gän
    -1.20
     consiguió
    -1.13
     Lorsque
    -1.12
     occasions
    -1.10
     vierten
    -1.10
     вариан
    -1.07
     penchant
    -1.05
     koup
    -1.05
     jener
    -1.03
    POSITIVE LOGITS
     for
    1.76
    provision
    1.45
     to
    1.29
    Provision
    1.25
     of
    1.25
     made
    1.09
     regarding
    1.08
     零
    1.05
     Provision
    1.03
    ÇÕES
    1.03
    Activations Density 0.007%

    No Known Activations