© 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. 3034
    Prev
    Next
    INDEX
    Explanations

    Russian Blue

    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
     excellente
    2.19
     presenta
    2.17
     পরীক্ষায়
    2.11
     avuto
    2.07
     duquel
    2.04
     இருந்தால்
    2.03
     permette
    2.01
    >−</
    1.98
     atender
    1.98
     entwickeln
    1.98
    POSITIVE LOGITS
    irov
    2.79
     باب
    2.52
    Ӣ
    2.45
     м
    2.41
    khov
    2.39
    ۖ
    2.36
     Kuznet
    2.35
    ська
    2.32
     Petrov
    2.32
     notified
    2.29
    Activations Density 0.639%

    No Known Activations