© 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. 237233
    Prev
    Next
    INDEX
    Explanations

    rights cancellation

    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
    Begriffsklär
    0.51
     Eğer
    0.49
     ઉત્પ
    0.47
    ászló
    0.46
    ů
    0.45
    uhà
    0.44
    ية
    0.44
    čku
    0.43
    发动
    0.43
     দুইজন
    0.43
    POSITIVE LOGITS
     meats
    0.49
     dilap
    0.47
     que
    0.46
     medicinal
    0.43
     agricultural
    0.42
     power
    0.42
     f
    0.42
     alimentation
    0.42
    w
    0.41
     grace
    0.41
    Activations Density 0.000%

    No Known Activations