© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2643
    Prev
    Next
    INDEX
    Explanations

    explaining in context

    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
    兔子
    1.91
    ອາ
    1.77
     compressive
    1.70
    ອາຫານ
    1.66
    compressed
    1.64
    ϓ
    1.64
     কান্না
    1.63
     عدم
    1.63
    羥
    1.63
     bukan
    1.59
    POSITIVE LOGITS
     transpired
    1.53
     pertains
    1.50
     stated
    1.42
     recently
    1.39
    avourites
    1.35
    ymptotic
    1.35
    cribes
    1.34
     pertain
    1.33
     postulated
    1.33
    foresaid
    1.29
    Activations Density 0.448%

    No Known Activations