© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19883
    Prev
    Next
    INDEX
    Explanations

    official correspondence

    np_acts-logits-general · gemini-2.5-flash-lite

    ; and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ћ
    0.50
    нология
    0.45
     переменных
    0.45
     élevés
    0.41
     빅
    0.41
     перемен
    0.41
    Fue
    0.41
    龛
    0.41
     соответствующих
    0.40
     Variables
    0.40
    POSITIVE LOGITS
     presupp
    0.51
     dismissing
    0.43
     isomeric
    0.43
     retali
    0.42
     obedient
    0.42
     submitting
    0.42
    orig
    0.41
    லய
    0.41
    女
    0.41
     erroneously
    0.40
    Activations Density 0.012%

    No Known Activations