© 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. 17326
    Prev
    Next
    INDEX
    Explanations

    grade level expectations

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

    version numbers and grades

    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
    🐽
    0.42
    🐷
    0.42
     ruj
    0.39
    👰
    0.38
    BtnUp
    0.37
    🐒
    0.37
     결혼
    0.37
    🐖
    0.37
    🚬
    0.36
    👛
    0.36
    POSITIVE LOGITS
    _
    0.45
    INV
    0.42
    ਪ
    0.41
    மெ
    0.40
     mời
    0.40
    НИ
    0.39
    中的
    0.39
    พาะ
    0.39
    ex
    0.38
    ভিং
    0.38
    Activations Density 0.000%

    No Known Activations