© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2707
    Prev
    Next
    INDEX
    Explanations

    provides code functionality

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

    sentences or spans of explanatory documentation/comments (long natural-language comments or docstrings) within code or text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     azonban
    0.14
    {
    0.14
     tetapi
    0.14
     ancak
    0.13
     ngayon
    0.12
     عبارت
    0.12
    ですが
    0.11
    ::
    0.11
     sljede
    0.11
     était
    0.11
    POSITIVE LOGITS
     Allows
    0.23
    для
    0.21
    Allows
    0.19
    untuk
    0.19
     Provides
    0.19
     тобто
    0.19
    Provides
    0.19
    important
    0.18
    provides
    0.18
    allowing
    0.18
    Activations Density 1.267%

    No Known Activations