© 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. 157444
    Prev
    Next
    INDEX
    Explanations

    blasting scouring

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

    intensity scales

    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
    。《
    0.57
    。『
    0.50
     dàng
    0.49
    。[
    0.46
     radically
    0.45
    。,
    0.45
     rén
    0.45
     xvi
    0.44
     принимает
    0.44
     са
    0.43
    POSITIVE LOGITS
    ชร์
    0.46
    ingar
    0.45
    and
    0.44
    waukee
    0.44
    intermedi
    0.43
    fähigkeit
    0.42
    athan
    0.41
    aktif
    0.41
    ‌و
    0.41
    ichtlich
    0.40
    Activations Density 0.000%

    No Known Activations