© 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. 110429
    Prev
    Next
    INDEX
    Explanations

    structured data and code

    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
     out
    -1.20
     From
    -1.13
     An
    -1.10
     Each
    -1.09
     To
    -1.08
     not
    -1.08
     With
    -1.05
     can
    -1.02
     In
    -1.02
     Not
    -1.02
    POSITIVE LOGITS
    hundreds
    1.33
     investissements
    1.18
    рецепт
    1.17
     struktur
    1.16
     aspek
    1.16
     infrastruktur
    1.15
    ironically
    1.15
     défis
    1.11
     kontro
    1.09
     fidé
    1.06
    Activations Density 0.001%

    No Known Activations