© 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. 40-GEMMASCOPE-2-RES-65K
    7. 2992
    Prev
    Next
    INDEX
    Explanations

    introducing lists of items

    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_40_width_65k_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
    some
    0.39
    Some
    0.38
    Lots
    0.37
     birçok
    0.37
    Many
    0.37
     wiele
    0.37
    a
    0.36
    部份
    0.36
    <unused2130>
    0.36
    全ての
    0.35
    POSITIVE LOGITS
     eerie
    0.47
     enigmatic
    0.43
     zusätzlichen
    0.41
     zusätzliche
    0.40
     inexplicable
    0.40
     ghostly
    0.40
     unorthodox
    0.40
     artistry
    0.39
     quirk
    0.39
     unwarranted
    0.38
    Activations Density 0.162%

    No Known Activations