© 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. 196694
    Prev
    Next
    INDEX
    Explanations

    new edition or change

    np_acts-logits-general · gemini-2.5-flash-lite

    Being followed by well

    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
     systém
    0.42
    for
    0.41
    สำหรับการ
    0.41
     る
    0.41
     acabado
    0.40
     holographic
    0.40
     bismuth
    0.40
     शकते
    0.39
    stocks
    0.39
     perjury
    0.39
    POSITIVE LOGITS
    रीन
    0.49
    玧
    0.48
     അത
    0.48
    InputStream
    0.46
    েইন
    0.45
    প্যাথ
    0.45
     givenChar
    0.45
    쳤
    0.45
    Ini
    0.45
    ogether
    0.44
    Activations Density 0.001%

    No Known Activations