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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49369
    Prev
    Next
    INDEX
    Explanations

    avoiding spam flags

    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
    㠱
    0.46
    ignée
    0.42
    ถุนายน
    0.42
     বপ
    0.40
    ጷ
    0.40
    㥳
    0.39
    ικο
    0.39
    getFull
    0.39
     прибли
    0.38
    zco
    0.38
    POSITIVE LOGITS
     sadly
    0.50
     wine
    0.48
     disappointing
    0.48
     meek
    0.48
     ಸಿ
    0.46
     warring
    0.45
     unbearable
    0.43
     跳
    0.43
     出
    0.43
     bling
    0.43
    Activations Density 0.014%

    No Known Activations