© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 195897
    Prev
    Next
    INDEX
    Explanations

    found and saved

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

    beauty of

    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
    赛事
    0.49
    연
    0.47
    数の
    0.47
    abo
    0.47
    ڑھ
    0.47
    अर
    0.46
    대
    0.46
     shenanigans
    0.45
    بری
    0.45
    াড়ি
    0.45
    POSITIVE LOGITS
     kön
    0.51
     governmental
    0.45
     lätt
    0.45
    檯
    0.44
    、(
    0.44
     ру
    0.44
     ruh
    0.44
     vat
    0.43
     lä
    0.43
     leicht
    0.43
    Activations Density 0.000%

    No Known Activations