© 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. 55357
    Prev
    Next
    INDEX
    Explanations

    when someone is

    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
    goài
    0.41
    Moz
    0.39
    árez
    0.39
    zag
    0.38
    ?=
    0.37
    ॉज
    0.37
    Popover
    0.37
    ErrorClazz
    0.37
    jár
    0.37
     നി
    0.37
    POSITIVE LOGITS
     Speedy
    0.45
     ouvre
    0.44
     Acc
    0.43
     #####
    0.42
     Scale
    0.41
     öff
    0.41
     Exempl
    0.40
     House
    0.40
     Divers
    0.40
     Opens
    0.40
    Activations Density 0.000%

    No Known Activations