© 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. 543
    Prev
    Next
    INDEX
    Explanations

    Imagick, agua, Dota, ad tech

    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
     S
    1.44
    S
    1.41
    SA
    1.24
    SL
    1.21
     Sl
    1.17
     SA
    1.16
    Sl
    1.14
    SR
    1.14
    GS
    1.14
    Ｓ
    1.11
    POSITIVE LOGITS
     Kiev
    0.83
     Kuk
    0.71
     mehndi
    0.66
     ultraviolet
    0.66
     Ultraviolet
    0.65
    indah
    0.65
     Chapel
    0.65
     Cohn
    0.64
     Kev
    0.64
     Boone
    0.64
    Activations Density 4.786%

    No Known Activations