© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99747
    Prev
    Next
    INDEX
    Explanations

    subsequent computations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    égard
    0.50
    towards
    0.47
    udahkan
    0.46
    incorrect
    0.45
    ownicy
    0.44
    స
    0.43
    σον
    0.43
     honourable
    0.43
    inertia
    0.43
    brightness
    0.42
    POSITIVE LOGITS
     athletics
    0.46
     erg
    0.42
     athleticism
    0.42
    ബ്ര
    0.42
     Dever
    0.42
     Atl
    0.41
    造
    0.41
     author
    0.40
    Ꮦ
    0.40
    產業
    0.39
    Activations Density 0.005%

    No Known Activations