© 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. 27321
    Prev
    Next
    INDEX
    Explanations

    instructions. advice. guidelines

    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
    I
    0.42
     дву
    0.42
     placards
    0.41
    Joy
    0.41
    WOW
    0.40
     if
    0.40
    Rose
    0.40
    Shar
    0.39
    Gr
    0.39
     जिंदा
    0.39
    POSITIVE LOGITS
     食
    0.45
    经
    0.45
    荸
    0.43
    経
    0.42
    大小
    0.42
     Artificial
    0.41
    緖
    0.41
     científ
    0.41
    經
    0.41
     學
    0.41
    Activations Density 0.000%

    No Known Activations