© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75748
    Prev
    Next
    INDEX
    Explanations

    specific audience context modify internal

    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/layer_31_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
    wunsch
    0.46
     ocorr
    0.46
     hou
    0.45
    ្អ
    0.45
     studi
    0.43
     量
    0.43
     órgano
    0.43
     guar
    0.43
     phép
    0.42
    工
    0.42
    POSITIVE LOGITS
     Abit
    0.46
    istič
    0.44
     Cermak
    0.44
     ساری
    0.44
     disagreed
    0.42
    Fuck
    0.40
    史上
    0.40
    cale
    0.39
    گیر
    0.39
     renovate
    0.39
    Activations Density 0.002%

    No Known Activations