© 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
    2. Gemma-3-270M
    3. 12-GEMMASCOPE-2-RES-16K
    4. 7104
    Prev
    Next
    INDEX
    Explanations

    apt-get install or update

    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_12_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
    oción
    2.30
    λευτα
    2.23
    鸯
    2.20
    hoo
    2.19
    ścić
    2.18
    teman
    2.16
     виду
    2.13
    Bowl
    2.13
    gekehrt
    2.09
    anders
    2.07
    POSITIVE LOGITS
    ный
    1.79
    ‍♀️
    1.55
    ные
    1.52
    atural
    1.50
     thự
    1.43
    勾
    1.43
    ного
    1.42
     digitalWrite
    1.39
    keiten
    1.39
     wobei
    1.38
    Activations Density 0.321%

    No Known Activations