© 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. 102813
    Prev
    Next
    INDEX
    Explanations

    glycine, flame, speed, interaction

    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
     Layton
    0.45
    繆
    0.41
    Telephone
    0.41
    摇头
    0.40
    電話
    0.40
     चिक
    0.40
    电话
    0.39
     Tel
    0.38
    Tel
    0.38
    mont
    0.38
    POSITIVE LOGITS
     interaction
    0.41
    toh
    0.37
     alternating
    0.36
     interacts
    0.36
    interacting
    0.35
    }$)
    0.35
     Submission
    0.35
     수상
    0.35
    晩
    0.35
     responds
    0.34
    Activations Density 0.001%

    No Known Activations