© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118617
    Prev
    Next
    INDEX
    Explanations

    incorporated herein by reference

    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
     get
    -1.73
     as
    -1.70
    With
    -1.63
     for
    -1.55
     provide
    -1.53
     should
    -1.52
     If
    -1.52
     did
    -1.52
     make
    -1.51
     had
    -1.50
    POSITIVE LOGITS
     frança
    1.73
     Diſ
    1.62
     ſen
    1.55
     bénéficiaire
    1.54
     allé
    1.53
     pensent
    1.52
    uestions
    1.47
     teint
    1.44
     cadeau
    1.43
    
    1.43
    Activations Density 0.059%

    No Known Activations