© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6706
    Prev
    Next
    INDEX
    Explanations

    whole wheat and whole grains

    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
    每
    1.70
     all
    1.57
    Mà
    1.44
    All
    1.43
    quire
    1.42
     شمالی
    1.32
     only
    1.32
    only
    1.30
    察
    1.29
    共
    1.28
    POSITIVE LOGITS
    heartedly
    2.57
     anderes
    2.41
    ologous
    2.36
    hearted
    2.31
    ething
    2.30
     nasty
    2.23
     bunch
    2.22
     monde
    2.22
     crap
    2.21
    otion
    2.21
    Activations Density 0.026%

    No Known Activations