© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126254
    Prev
    Next
    INDEX
    Explanations

    categorized by function, technology, age

    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_31_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
    ers
    0.47
    çoivent
    0.45
    engan
    0.44
     encompasses
    0.44
    ецца
    0.43
    ّل
    0.43
    ᄌ
    0.40
     teammate
    0.39
    ᄋ
    0.39
     statewide
    0.39
    POSITIVE LOGITS
     pris
    0.43
     সেবা
    0.42
    seb
    0.41
     gripe
    0.41
     দেবযানী
    0.41
     tomon
    0.40
     Prestige
    0.39
     dementia
    0.39
     मानव
    0.39
     নূতন
    0.38
    Activations Density 0.011%

    No Known Activations