© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5939
    Prev
    Next
    INDEX
    Explanations

    choose or select

    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
     prospecting
    1.08
    ictal
    1.00
    enangkan
    0.93
     kaynağından
    0.93
    pine
    0.90
    运气
    0.89
    讼
    0.87
    acoes
    0.86
    イナー
    0.85
    泄
    0.84
    POSITIVE LOGITS
    ocode
    1.29
    comic
    1.29
     jeans
    1.29
    shirts
    1.29
    comics
    1.28
    Ahmed
    1.28
    ادم
    1.28
    rash
    1.27
     shirts
    1.26
    knit
    1.23
    Activations Density 0.069%

    No Known Activations