© 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. 128330
    Prev
    Next
    INDEX
    Explanations

    abstract object properties

    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
     réduit
    0.47
    用餐
    0.47
     labels
    0.46
     plummeted
    0.46
    向下
    0.45
     oiled
    0.45
    ي
    0.45
    转
    0.44
     planes
    0.43
    ݢ
    0.43
    POSITIVE LOGITS
    ına
    0.57
    ribute
    0.50
    icin
    0.46
    en
    0.44
    ın
    0.44
    ean
    0.44
    ingen
    0.43
    her
    0.43
    awa
    0.42
    iving
    0.42
    Activations Density 0.002%

    No Known Activations