© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16212
    Prev
    Next
    INDEX
    Explanations

    mathematical notation following markers

    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
    are
    1.48
    ut
    1.46
    '
    1.35
    u
    1.34
    is
    1.30
    as
    1.27
    ih
    1.22
    the
    1.21
    oo
    1.21
    w
    1.21
    POSITIVE LOGITS
    ，
    1.47
    、
    1.17
    。
    1.13
    ،
    1.11
    كَ
    1.05
    قة
    1.02
    います
    0.93
    。《
    0.91
     \
    0.85
     desenvolved
    0.82
    Activations Density 0.007%

    No Known Activations