© 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. 10629
    Prev
    Next
    INDEX
    Explanations

    why, turn, pull

    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
    जनबी
    2.79
    ινό
    2.62
    λλη
    2.53
    мот
    2.47
     σχέ
    2.45
    ritas
    2.44
    ার
    2.44
    窕
    2.41
    द्धांत
    2.37
    rious
    2.33
    POSITIVE LOGITS
    𝓱
    2.36
    치
    2.17
    empot
    2.09
    ãi
    2.08
    ikation
    2.06
    els
    2.06
    eles
    2.01
    iet
    1.97
     posto
    1.97
    ers
    1.96
    Activations Density 0.011%

    No Known Activations