© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12539
    Prev
    Next
    INDEX
    Explanations

    ask me anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ه
    2.13
    ে
    1.97
    ം
    1.95
    м
    1.90
    ה
    1.85
    iť
    1.84
    o
    1.77
    a
    1.75
    ხილ
    1.73
    eing
    1.73
    POSITIVE LOGITS
     varsity
    1.48
     boxe
    1.45
     dy
    1.43
    rivel
    1.42
     amu
    1.42
     elektrik
    1.39
     bouche
    1.38
     thoại
    1.38
     saya
    1.37
    atchewan
    1.36
    Activations Density 0.004%

    No Known Activations