© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 43305
    Prev
    Next
    INDEX
    Explanations

    "What is" question intros

    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_16_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
    ాలు
    0.96
    that
    0.95
     není
    0.95
    用
    0.90
    ována
    0.89
    have
    0.88
    ో
    0.86
    rás
    0.83
    ovány
    0.83
    状況
    0.82
    POSITIVE LOGITS
     in
    1.83
     for
    1.42
     is
    1.29
     can
    1.29
     be
    1.21
     has
    1.21
     I
    1.15
    !
    1.13
     *
    1.07
     the
    1.05
    Activations Density 0.076%

    No Known Activations