© 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. 197762
    Prev
    Next
    INDEX
    Explanations

    common word sequences

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

    streaks of rain

    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
     大きい
    0.49
    まとめ
    0.49
    大きい
    0.49
    මාණ
    0.47
    퐶
    0.47
    その他の
    0.47
    ました
    0.46
    競
    0.46
    тель
    0.46
    いただきました
    0.46
    POSITIVE LOGITS
     argent
    0.51
     immers
    0.45
     acier
    0.44
     arable
    0.44
     οποίο
    0.43
     plonge
    0.43
     obliquely
    0.43
     pozwala
    0.42
     impos
    0.42
     allowing
    0.42
    Activations Density 0.001%

    No Known Activations