© 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. 668
    Prev
    Next
    INDEX
    Explanations

    language transformations

    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
    it
    1.06
    ish
    1.00
    .
    0.99
    ,
    0.98
    y
    0.94
    ik
    0.94
    !
    0.93
    oc
    0.93
    /
    0.92
    ie
    0.90
    POSITIVE LOGITS
    GTUIKit
    2.06
     ہُما
    2.04
    𒅅
    2.04
    𒌍
    2.00
    𒀠
    2.00
    𒆗
    2.00
    𒀊
    1.99
     algéb
    1.98
    𒌦
    1.96
    𒉋
    1.96
    Activations Density 0.183%

    No Known Activations