© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3318
    Prev
    Next
    INDEX
    Explanations

    elaborate on

    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_7_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
    tio
    2.93
    sí
    2.83
    이트
    2.76
    тков
    2.60
    ください
    2.57
    IENTS
    2.55
    таки
    2.54
    י
    2.50
    tive
    2.49
    zka
    2.44
    POSITIVE LOGITS
    ded
    2.27
     pari
    2.26
    emed
    2.23
    ding
    2.11
     aant
    2.08
    elig
    2.06
    emu
    2.06
    𝑒
    2.05
    𝑖
    2.04
    arto
    1.96
    Activations Density 0.028%

    No Known Activations