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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69521
    Prev
    Next
    INDEX
    Explanations

    my/py prefixes

    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_15_width_262k_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
    mangle
    1.84
     народного
    1.84
     самая
    1.81
    وتن
    1.74
    ٥
    1.73
    령
    1.71
     powod
    1.68
     налого
    1.66
    会儿
    1.65
     puissent
    1.64
    POSITIVE LOGITS
     subgoal
    1.34
    iales
    1.10
    preter
    1.04
    escue
    1.03
    撇
    1.01
    ías
    0.98
    abolism
    0.97
    vio
    0.97
    CoO
    0.95
    za
    0.95
    Activations Density 0.000%

    No Known Activations