© 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. 63953
    Prev
    Next
    INDEX
    Explanations

    "TO" or "to" followed by punctuation/colon

    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
    >'
    0.43
     цього
    0.39
    ©
    0.38
     Distributor
    0.38
     Globo
    0.38
     %>
    0.38
     Sources
    0.37
    ('<
    0.37
     Sand
    0.37
    sand
    0.36
    POSITIVE LOGITS
    voluntary
    0.44
    ){\
    0.43
    ᾷ
    0.42
    "][
    0.41
    ][
    0.40
    لوث
    0.40
    ":{"
    0.40
     ferrite
    0.39
    abling
    0.39
     iteratively
    0.38
    Activations Density 0.000%

    No Known Activations