© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2354
    Prev
    Next
    INDEX
    Explanations

    fill the container

    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
    %"},
    1.87
    🥅
    1.85
    scalars
    1.81
     ponieważ
    1.79
     sofern
    1.78
     coveredmethods
    1.78
     sodass
    1.77
    ामान्य
    1.77
     sobald
    1.75
     bewe
    1.75
    POSITIVE LOGITS
    oman
    1.55
    ­
    1.44
    ,
    1.34
    os
    1.34
    unting
    1.32
    ya
    1.32
     This
    1.32
     cracker
    1.32
    ธิ
    1.31
     বলিয়া
    1.31
    Activations Density 0.089%

    No Known Activations