© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13526
    Prev
    Next
    INDEX
    Explanations

    discussing games and technology

    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_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
     agacch
    1.37
     やつ
    1.36
     从
    1.32
     ㅋㅋ
    1.31
     tesam
    1.29
     hahaha
    1.28
     প্রাসাদ
    1.26
     fester
    1.26
     덕
    1.26
     nisid
    1.25
    POSITIVE LOGITS
    recorded
    1.04
    able
    1.04
    amura
    1.03
    上网
    0.99
    anti
    0.98
     recorded
    0.95
    ere
    0.92
    iaz
    0.90
    ací
    0.89
    ทาง
    0.88
    Activations Density 0.887%

    No Known Activations