© 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. 16-GEMMASCOPE-2-RES-262K
    7. 137596
    Prev
    Next
    INDEX
    Explanations

    Bulgarian, Bengal

    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
     in
    1.13
    k
    1.05
    s
    1.02
    h
    0.91
    d
    0.91
     as
    0.89
    n
    0.89
    b
    0.85
    g
    0.83
     he
    0.80
    POSITIVE LOGITS
    ু
    0.90
    ﻟ
    0.82
    ﻋ
    0.75
    цами
    0.73
    ﻷ
    0.72
    ﺯ
    0.71
    ﺭ
    0.71
    izarea
    0.70
    YOUR
    0.69
    ши
    0.68
    Activations Density 0.001%

    No Known Activations