© 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. 16928
    Prev
    Next
    INDEX
    Explanations

    parts of a whole

    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
    t
    1.04
    of
    1.00
    the
    0.98
    f
    0.93
     part
    0.91
     nombre
    0.86
     financi
    0.85
    Y
    0.84
    ین
    0.81
    in
    0.81
    POSITIVE LOGITS
     parts
    1.38
    teile
    1.22
    Parts
    1.21
    parts
    1.20
     Parts
    1.15
     PARTS
    1.01
     to
    0.93
    د
    0.93
     Teile
    0.91
     on
    0.90
    Activations Density 0.009%

    No Known Activations