© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1680
    Prev
    Next
    INDEX
    Explanations

    ancient civilizations and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
     browns
    1.36
     rosem
    1.32
    olor
    1.19
     melanin
    1.16
     Valentino
    1.16
    brown
    1.16
    얀
    1.15
     Fannie
    1.14
    Isl
    1.14
     fermion
    1.13
    POSITIVE LOGITS
    consum
    1.63
    紂
    1.60
    tablet
    1.56
    纣
    1.55
     BCE
    1.51
     حدا
    1.50
     поку
    1.47
    勸
    1.46
    ביל
    1.45
     eph
    1.45
    Activations Density 0.119%

    No Known Activations