© 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. 5700
    Prev
    Next
    INDEX
    Explanations

    step-by-step instructions

    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
    pz
    1.91
    月底
    1.81
    誌
    1.78
    estado
    1.77
    fst
    1.73
    ộc
    1.71
    ungg
    1.70
     atteggi
    1.69
     biofilm
    1.67
    ppable
    1.66
    POSITIVE LOGITS
    Bahn
    1.45
     termes
    1.26
    !
    1.12
     Viol
    1.10
     musicales
    1.10
    的处理
    1.07
    !»
    1.06
     lahat
    1.06
    Viol
    1.05
    eglasses
    1.05
    Activations Density 0.004%

    No Known Activations