© 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. 41-GEMMASCOPE-2-RES-262K
    7. 7952
    Prev
    Next
    INDEX
    Explanations

    section separators

    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
    ᱼ
    0.36
     \\
    0.34
    ktCap
    0.32
    。」
    0.32
     antisymmetric
    0.32
    ಙ
    0.31
     computes
    0.31
    acetyl
    0.31
    ្សែ
    0.31
    VERSION
    0.31
    POSITIVE LOGITS
    Д
    0.50
    У
    0.49
    М
    0.49
    Б
    0.49
    В
    0.48
    Ма
    0.48
    К
    0.48
    По
    0.47
    П
    0.46
    На
    0.45
    Activations Density 0.274%

    No Known Activations