© 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. 35403
    Prev
    Next
    INDEX
    Explanations

    already followed by descriptor

    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
    a
    0.91
    includes
    0.72
    of
    0.71
    endo
    0.71
    ihe
    0.70
    troops
    0.70
    اً
    0.68
    sj
    0.68
    limits
    0.67
    lot
    0.67
    POSITIVE LOGITS
     resur
    0.58
    タ
    0.57
     manager
    0.56
     privilege
    0.56
     survivor
    0.55
     immun
    0.54
    ですが
    0.54
     frustration
    0.53
     slab
    0.52
     fragile
    0.52
    Activations Density 0.004%

    No Known Activations