© 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. 11986
    Prev
    Next
    INDEX
    Explanations

    explicit statements

    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
     данными
    0.41
     kapas
    0.40
    matcher
    0.40
    পাল
    0.40
     streetlight
    0.39
     retrie
    0.39
    鳩
    0.39
    払い
    0.38
     CLEAN
    0.38
     இணைந்து
    0.37
    POSITIVE LOGITS
     explicitly
    0.91
     предупре
    0.85
     explicit
    0.84
    explicit
    0.82
    Explicit
    0.80
    明确
    0.80
    告知
    0.80
     Explicit
    0.79
     openly
    0.78
     warn
    0.77
    Activations Density 0.404%

    No Known Activations