© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1009
    Prev
    Next
    INDEX
    Explanations

    United States

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selben
    0.93
     unchanged
    0.84
     UNNEEDED
    0.79
    侘
    0.78
    ochen
    0.77
    ießen
    0.75
     Discreet
    0.75
    antoor
    0.69
     löyty
    0.68
    idze
    0.68
    POSITIVE LOGITS
     Kingdom
    1.61
     States
    1.53
     sett
    1.52
    States
    1.48
     kingdom
    1.48
     Kd
    1.45
     Hebre
    1.42
    แต
    1.40
    複
    1.39
     Wap
    1.38
    Activations Density 0.444%

    No Known Activations