© 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. 52376
    Prev
    Next
    INDEX
    Explanations

    just because

    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
     वापसी
    0.46
     ಇಲ್ಲ
    0.46
    鋈
    0.43
    ائية
    0.43
    ята
    0.42
    iele
    0.41
    mez
    0.40
    ле
    0.39
    èt
    0.39
     واپسی
    0.39
    POSITIVE LOGITS
     understandably
    0.48
     rozwo
    0.43
     amply
    0.42
    s
    0.42
     crucially
    0.41
     began
    0.41
     Wilbur
    0.41
     principales
    0.41
    some
    0.41
     Stro
    0.40
    Activations Density 0.003%

    No Known Activations