© 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. 79127
    Prev
    Next
    INDEX
    Explanations

    foreign language or symbols

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

    basic headers understanding specific

    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
    ריה
    0.47
     دی۔
    0.45
     거예요
    0.45
    ،
    0.45
    کان
    0.44
    ویز
    0.44
    hiro
    0.43
     prompted
    0.43
     शरी
    0.43
     مک
    0.42
    POSITIVE LOGITS
    ди
    0.46
     pecans
    0.45
    ে
    0.43
     однако
    0.42
    aient
    0.42
    {
    0.42
     όμως
    0.42
     orchards
    0.41
     swamps
    0.41
    нді
    0.41
    Activations Density 0.000%

    No Known Activations