© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150642
    Prev
    Next
    INDEX
    Explanations

    phrases like "in particular", "sponsored programs", "never dull"

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptive modifiers to nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    밝
    0.50
    氙
    0.49
    PanelVisual
    0.46
    קת
    0.46
    仅
    0.45
    并行
    0.45
    骶
    0.45
     powerAll
    0.44
    πι
    0.44
    ז
    0.44
    POSITIVE LOGITS
     of
    0.63
     manufactures
    0.52
     western
    0.51
     Institute
    0.50
    western
    0.50
     at
    0.49
     international
    0.49
     East
    0.48
     warehouses
    0.48
     multinational
    0.48
    Activations Density 0.000%

    No Known Activations