© 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. 199895
    Prev
    Next
    INDEX
    Explanations

    management and methods

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

    shallow water

    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
    <h1>
    0.50
    T
    0.48
    后
    0.45
    cur
    0.45
    وسي
    0.43
    col
    0.43
    住宅
    0.43
    联邦
    0.42
    当前
    0.41
    يرا
    0.41
    POSITIVE LOGITS
     ампли
    0.50
     入り
    0.49
    淺
    0.47
     ढूं
    0.47
     変
    0.47
    ЛЬ
    0.46
     상담
    0.46
    눌
    0.46
    pengaruhi
    0.46
     शब्दा
    0.46
    Activations Density 0.000%

    No Known Activations