© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13029
    Prev
    Next
    INDEX
    Explanations

    introduction of concepts or specific entities

    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
     흡
    0.48
     비롯
    0.46
    슐
    0.45
    Σ
    0.43
     Highways
    0.43
    手順
    0.43
    ཋ
    0.43
    Customers
    0.42
    తాయి
    0.42
    뮐
    0.41
    POSITIVE LOGITS
    ok
    0.41
     is
    0.40
    ampu
    0.40
     Godfather
    0.40
     summer
    0.40
     Jane
    0.40
     orphanage
    0.40
    addam
    0.39
    arl
    0.39
    ী
    0.39
    Activations Density 0.002%

    No Known Activations