© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 6997
    Prev
    Next
    INDEX
    Explanations

    commas and specific terms

    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_all/layer_41_width_262k_l0_big
    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
    ----\
    0.42
    因
    0.41
    вич
    0.40
    čiu
    0.39
    ಆ
    0.39
     любом
    0.38
    周囲
    0.38
     yourselves
    0.38
    ല്ലാം
    0.38
    ivät
    0.38
    POSITIVE LOGITS
     baz
    0.41
    acids
    0.39
    Basil
    0.39
     Basil
    0.39
     Fossil
    0.39
     Firmen
    0.39
    驥
    0.39
     Gord
    0.38
     vorbere
    0.38
    பசு
    0.38
    Activations Density 0.004%

    No Known Activations