© 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. 10946
    Prev
    Next
    INDEX
    Explanations

    LZW encoding

    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
    ều
    2.16
    ne
    1.96
    ung
    1.94
    umbi
    1.92
    ai
    1.91
    falls
    1.89
    ùa
    1.84
    h
    1.84
    ennium
    1.78
    ale
    1.77
    POSITIVE LOGITS
    Ḫ
    3.08
     тру
    3.06
    arrerol
    2.95
    ीट
    2.94
     puriso
    2.85
    醿
    2.83
    omorphisms
    2.82
    𐱅
    2.82
    াহিয়া
    2.79
    ORICAL
    2.79
    Activations Density 0.007%

    No Known Activations