© 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. 11060
    Prev
    Next
    INDEX
    Explanations

    synths

    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
     ‘
    1.85
     ’
    1.76
     館
    1.68
     桌
    1.57
     單
    1.53
     红
    1.52
     他们
    1.52
     時間
    1.52
     對
    1.51
     今天
    1.51
    POSITIVE LOGITS
    ₁.
    1.65
     కానీ
    1.63
     artériel
    1.55
     bildet
    1.48
    Essential
    1.45
     défini
    1.43
    ⏟
    1.42
    บาล
    1.41
    つまり
    1.41
    specified
    1.40
    Activations Density 0.038%

    No Known Activations