© 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. 106535
    Prev
    Next
    INDEX
    Explanations

    gets messy or worse

    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
     Corolle
    0.64
    ﭼ
    0.64
     massimo
    0.63
    Ꭳ
    0.63
    arikat
    0.62
     kanggo
    0.62
     professores
    0.61
     হান
    0.61
     herhangi
    0.61
    ার্চ
    0.61
    POSITIVE LOGITS
    OT
    0.66
    over
    0.61
    TO
    0.60
     be
    0.59
     I
    0.58
    Gets
    0.57
    OR
    0.55
    UT
    0.54
    oded
    0.54
    It
    0.53
    Activations Density 0.017%

    No Known Activations