© 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. 3487
    Prev
    Next
    INDEX
    Explanations

    python code and functions

    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
    騷
    1.86
     dukkh
    1.79
    暫
    1.64
    iggers
    1.63
     hali
    1.59
     natthi
    1.59
     vises
    1.58
    ้าย
    1.57
    permal
    1.57
     vab
    1.56
    POSITIVE LOGITS
     Papp
    1.26
     mankind
    1.20
     telescop
    1.19
     deduction
    1.18
    tze
    1.16
     infallible
    1.15
     Booster
    1.14
    ²+
    1.12
     Optimization
    1.11
     }{
    1.10
    Activations Density 0.000%

    No Known Activations