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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 273
    Prev
    Next
    INDEX
    Explanations

    attempt quickly

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

    enables or causes outcomes

    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_16k_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
    ۔
    0.35
    。
    0.34
    '.
    0.31
    ።
    0.31
    》。
    0.29
    ।
    0.28
     کی۔
    0.28
     क्योंकि
    0.27
    ’.
    0.27
    *.
    0.27
    POSITIVE LOGITS
     makes
    0.50
     ensures
    0.47
     enables
    0.46
     gives
    0.45
     provides
    0.43
     brings
    0.42
     zorgt
    0.41
     creates
    0.41
     underlies
    0.41
     helps
    0.40
    Activations Density 2.263%

    No Known Activations