© 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. 110600
    Prev
    Next
    INDEX
    Explanations

    ignores a variable

    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
    ון
    0.55
     liquido
    0.51
    지와
    0.48
     শেষের
    0.48
    eating
    0.47
     ربعه
    0.47
    ץ
    0.46
    ی
    0.44
    ین
    0.44
    ات
    0.44
    POSITIVE LOGITS
     forms
    0.45
    ज़ी
    0.44
    ल
    0.44
     idiom
    0.43
    妵
    0.41
     rr
    0.41
    सूस
    0.41
     amiga
    0.41
     род
    0.40
     multilingual
    0.39
    Activations Density 0.006%

    No Known Activations