© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4016
    Prev
    Next
    INDEX
    Explanations

    A customer of AWE Network

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ン
    0.43
     citrus
    0.41
     inspirations
    0.39
     saltwater
    0.39
     화학
    0.38
     agglomer
    0.37
     reformulation
    0.37
     ترکیب
    0.37
    atorul
    0.37
    レッ
    0.37
    POSITIVE LOGITS
    ς
    0.46
    haben
    0.41
    richt
    0.38
    s
    0.38
    pread
    0.38
     égale
    0.38
    bezier
    0.37
    dds
    0.37
    妩
    0.37
    γκ
    0.36
    Activations Density 0.001%

    No Known Activations