© 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. 229427
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    4
    0.51
    2
    0.50
    3
    0.48
    5
    0.46
     spatula
    0.46
    8
    0.46
     yolk
    0.45
    まずは
    0.45
    9
    0.45
    1
    0.44
    POSITIVE LOGITS
    ască
    0.46
    achery
    0.44
    ünstler
    0.43
    كان
    0.43
    Intersect
    0.43
     begrip
    0.42
     kontek
    0.42
    bücher
    0.41
    aker
    0.40
    chnet
    0.40
    Activations Density 0.002%

    No Known Activations