© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3686
    Prev
    Next
    INDEX
    Explanations

    Winner comparison

    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_65k_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
    d
    0.57
    t
    0.54
    h
    0.49
    dar
    0.46
    s
    0.44
     pathological
    0.44
    dans
    0.43
    dab
    0.43
    ாவில்
    0.42
    ด์
    0.42
    POSITIVE LOGITS
     nhưng
    0.47
     IF
    0.47
     area
    0.46
     áreas
    0.45
     Ү
    0.45
     تغ
    0.45
     కానీ
    0.44
     areas
    0.43
     KMS
    0.43
     কিন্তু
    0.42
    Activations Density 0.013%

    No Known Activations