© 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-65K
    7. 3751
    Prev
    Next
    INDEX
    Explanations

    python code, load, following, sells

    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_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
     familiari
    1.43
     fonti
    1.41
    rir
    1.38
     recognises
    1.38
     („
    1.36
    녈
    1.30
     dijete
    1.28
    ([(
    1.26
     biographer
    1.25
     illustrating
    1.25
    POSITIVE LOGITS
     сути
    1.61
     نهایت
    1.51
     auc
    1.50
    льше
    1.50
    akami
    1.49
    intersection
    1.49
     MSE
    1.49
     lowercase
    1.48
     func
    1.47
     supre
    1.46
    Activations Density 0.056%

    No Known Activations