© 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. 11364
    Prev
    Next
    INDEX
    Explanations

    heating as a cooking step

    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
    ي
    2.34
    ્ટ
    2.18
     таки
    1.86
    ร์
    1.84
    p
    1.82
    y
    1.79
    Quite
    1.78
    ту
    1.78
    ल
    1.77
    प
    1.76
    POSITIVE LOGITS
    ebab
    2.19
    ský
    2.00
    ブル
    1.98
    aeus
    1.79
     pemilihan
    1.76
    ocio
    1.75
     regering
    1.75
    ékek
    1.75
    aczego
    1.73
    volvimento
    1.72
    Activations Density 0.012%

    No Known Activations