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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1220
    Prev
    Next
    INDEX
    Explanations

    multilingual words and punctuation

    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_16_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
    or
    0.53
    د
    0.49
    IO
    0.48
    rera
    0.48
    ak
    0.46
     máme
    0.46
    h
    0.46
    ut
    0.44
    kinson
    0.44
    SIM
    0.44
    POSITIVE LOGITS
    ک
    0.46
    გ
    0.44
     inextricably
    0.43
    ຜະລິດຕະພັນ
    0.43
    코
    0.43
    점에서
    0.42
    로
    0.42
    Про
    0.41
     Millionen
    0.41
    세계
    0.40
    Activations Density 0.576%

    No Known Activations