© 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. 192660
    Prev
    Next
    INDEX
    Explanations

    descriptive states or statuses

    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_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
    摑
    0.45
    fluss
    0.42
     titre
    0.42
    rights
    0.40
    łka
    0.40
    }}}\
    0.40
     reductase
    0.40
    upsilon
    0.40
     औरत
    0.39
    權
    0.38
    POSITIVE LOGITS
    ാമ
    0.37
     effortlessly
    0.36
    訲
    0.35
     party
    0.35
    Ч
    0.34
    Party
    0.34
     హి
    0.34
     visão
    0.33
    زاب
    0.33
     preparations
    0.33
    Activations Density 0.000%

    No Known Activations