© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4758
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting

    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
     Compliance
    0.28
     packageName
    0.28
     microns
    0.28
     disguise
    0.27
     pageSize
    0.27
    崤
    0.26
     patina
    0.26
    噘
    0.26
     Oxide
    0.25
     retouch
    0.25
    POSITIVE LOGITS
    ம்
    0.32
    も
    0.32
    ک
    0.30
    in
    0.28
    ボ
    0.28
    ko
    0.27
    more
    0.27
    iv
    0.27
    する
    0.26
    derick
    0.26
    Activations Density 0.000%

    No Known Activations