© 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-65K
    7. 3673
    Prev
    Next
    INDEX
    Explanations

    website descriptions, titles, and classifications

    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_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
    ли
    1.20
    (
    1.11
    in
    1.07
    de
    1.07
    ни
    1.06
    ：
    1.04
    p
    1.02
    د
    1.02
    s
    1.01
    h
    1.00
    POSITIVE LOGITS
    0.80
     unteren
    0.66
     гэта
    0.66
     privaten
    0.65
    玩笑
    0.65
     terecht
    0.65
    不是很
    0.63
     äh
    0.61
     possesses
    0.60
     bless
    0.59
    Activations Density 0.164%

    No Known Activations