© 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. 89610
    Prev
    Next
    INDEX
    Explanations

    dynamically creating/updating/choosing

    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
    쐐
    0.68
     involunt
    0.60
    饺
    0.59
    弧
    0.59
     اربع
    0.58
    ф
    0.57
     bijective
    0.57
     redundancies
    0.56
    АН
    0.55
     하나의
    0.55
    POSITIVE LOGITS
     o
    0.78
     Default
    0.71
     me
    0.63
     Lists
    0.63
     c
    0.61
     s
    0.60
     De
    0.60
    o
    0.59
     e
    0.59
     Class
    0.59
    Activations Density 0.030%

    No Known Activations