© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4429
    Prev
    Next
    INDEX
    Explanations

    I understand, ready

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     이용하여
    1.13
     hereafter
    1.06
     advices
    1.05
    等が
    1.03
     ########
    1.02
     approximate
    1.00
    angulo
    0.98
     }},
    0.98
    の為
    0.97
    []}
    0.93
    POSITIVE LOGITS
     месяцев
    2.04
    يّ
    2.02
     тво
    2.01
     кры
    2.00
     меся
    1.96
     февра
    1.96
     изобре
    1.94
     утвер
    1.92
     пър
    1.91
    ّ
    1.90
    Activations Density 0.442%

    No Known Activations