© 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. 15091
    Prev
    Next
    INDEX
    Explanations

    specific items followed by commas

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

    items followed by commas

    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
    cribing
    0.48
    際に
    0.47
     />;
    0.47
    0.45
    ங்களும்
    0.45
     čega
    0.44
    人和
    0.43
    ంతా
    0.43
    =")
    0.43
    acuse
    0.43
    POSITIVE LOGITS
    ،
    2.22
    ，
    1.96
    ၊
    1.83
    ,
    1.74
    ፣
    1.63
    、
    1.48
    ,,
    1.47
    ,_
    1.46
     ،
    1.42
    ,<
    1.42
    Activations Density 0.620%

    No Known Activations