© 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. 5028
    Prev
    Next
    INDEX
    Explanations

    harmless AI

    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
     Mosca
    1.62
     собственного
    1.48
     жа
    1.48
    Unnamed
    1.47
     страш
    1.45
     филь
    1.44
    淥
    1.44
    чен
    1.44
     каких
    1.44
    捶
    1.44
    POSITIVE LOGITS
    ength
    1.49
    pectives
    1.23
    พย์
    1.22
    ytically
    1.15
    ingham
    1.14
     offici
    1.14
     ระยะ
    1.12
     seamlessly
    1.12
    kuat
    1.12
    chter
    1.11
    Activations Density 0.008%

    No Known Activations