© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107911
    Prev
    Next
    INDEX
    Explanations

    currency conversion

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

    value, harm, campaign

    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
    蒺
    0.47
    💨
    0.46
    ěstí
    0.45
     vutta
    0.43
    istasis
    0.43
    드를
    0.42
    سری
    0.42
     त्य
    0.42
    আমরা
    0.41
     кожного
    0.41
    POSITIVE LOGITS
    value
    0.58
     value
    0.54
     VALUE
    0.51
     harmonization
    0.50
     Value
    0.49
    长
    0.49
    Value
    0.48
    値
    0.46
     values
    0.46
     waarde
    0.46
    Activations Density 0.001%

    No Known Activations