© 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. 152276
    Prev
    Next
    INDEX
    Explanations

    edition, generally, your, for, protection, Prime, get

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

    french techno dance duos

    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
    準備
    0.45
    yourself
    0.41
    ⁣⁣
    0.41
    准备
    0.40
    before
    0.39
    きっと
    0.39
    must
    0.39
    ‼️
    0.39
    💫
    0.39
     रहिए
    0.38
    POSITIVE LOGITS
     mivel
    0.46
     handgun
    0.45
     väik
    0.45
     electricidad
    0.45
     ஏனெனில்
    0.44
     चूंकि
    0.43
     elektrom
    0.43
     हालांकि
    0.42
     hauptsächlich
    0.42
     obwohl
    0.42
    Activations Density 0.003%

    No Known Activations