© 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. 959
    Prev
    Next
    INDEX
    Explanations

    shall speak

    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
     spirit
    0.50
    靈
    0.47
    Quiet
    0.44
     precious
    0.43
     just
    0.43
     joy
    0.40
    ulele
    0.40
    begin
    0.40
     Western
    0.40
    iy
    0.40
    POSITIVE LOGITS
     いつ
    0.58
     लगातार
    0.57
     зло
    0.56
     rubrique
    0.56
     дети
    0.55
    Ấ
    0.55
     fraudulent
    0.55
     authorizes
    0.54
     тонн
    0.54
    гляда
    0.54
    Activations Density 0.000%

    No Known Activations