© 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. 58978
    Prev
    Next
    INDEX
    Explanations

    for more details

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

    find more information

    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
    ：
    0.48
     ہوا۔
    0.44
     کی۔
    0.44
    。
    0.43
    ]:
    0.41
     arba
    0.41
    やっと
    0.40
    :
    0.40
    ।
    0.39
    !:
    0.39
    POSITIVE LOGITS
     자세
    0.65
    詳しい
    0.64
    詳細は
    0.63
     details
    0.60
     détails
    0.59
    詳細
    0.57
     detailed
    0.56
     detal
    0.54
     detalhes
    0.54
    詳しくは
    0.54
    Activations Density 0.078%

    No Known Activations