© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 2517
    Prev
    Next
    INDEX
    Explanations

    resources that

    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
    als
    1.22
    att
    1.13
    ich
    1.09
    utter
    1.04
    atch
    1.00
    arch
    1.00
    under
    0.98
    w
    0.98
    otricha
    0.97
    over
    0.97
    POSITIVE LOGITS
     klasik
    1.48
     này
    1.39
     zvyš
    1.37
     tertinggi
    1.35
     jednotliv
    1.35
     tertentu
    1.35
     této
    1.34
     különböző
    1.34
     masyarakat
    1.34
     ilmiah
    1.33
    Activations Density 0.017%

    No Known Activations