© 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. 3187
    Prev
    Next
    INDEX
    Explanations

    The core, piece, function, flies, enough, initial, for

    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
    実
    1.62
     jsx
    1.53
    样式
    1.51
    元素的
    1.50
    整體
    1.49
    鍵
    1.49
     внима
    1.48
     diseño
    1.48
    ்கலை
    1.48
     `:`
    1.46
    POSITIVE LOGITS
    lad
    1.12
    rp
    1.10
     biting
    1.10
     Pim
    1.09
    pl
    1.07
     strangled
    1.07
    zam
    1.07
    rap
    1.06
    W
    1.06
    pre
    1.06
    Activations Density 0.053%

    No Known Activations