© 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. 58558
    Prev
    Next
    INDEX
    Explanations

    neutral, play, Single, React, password, shall

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

    different languages and grammatical roles

    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
     psych
    0.48
    ,
    0.47
     neuropath
    0.47
    ation
    0.47
     speck
    0.46
     consequent
    0.46
     algebra
    0.44
     precipitate
    0.44
     elves
    0.44
     ("
    0.43
    POSITIVE LOGITS
    если
    0.76
    ที่
    0.72
    ใน
    0.71
    sorry
    0.70
    כ
    0.68
    ?).
    0.67
    หรือ
    0.66
    после
    0.66
    laughs
    0.65
    在
    0.64
    Activations Density 0.000%

    No Known Activations