© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2805
    Prev
    Next
    INDEX
    Explanations

    mirror, representative, prepared

    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_13_width_65k_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
     دہشت
    1.76
    öner
    1.72
    武
    1.64
    ímos
    1.63
    μαι
    1.59
    なんです
    1.57
    stringValue
    1.57
    ಿದ್ದೇವೆ
    1.57
    しております
    1.57
    țile
    1.56
    POSITIVE LOGITS
    /
    1.45
    ,
    1.32
    :
    1.24
    創意
    1.15
     levelled
    1.10
     bagged
    1.09
    _/
    1.08
     Bayou
    1.08
     yielded
    1.03
     scooped
    1.03
    Activations Density 0.000%

    No Known Activations