© 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. 12355
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
    ะ
    1.76
     board
    1.66
    it
    1.50
     sound
    1.46
     check
    1.44
     rada
    1.43
     system
    1.42
     operation
    1.42
    يبة
    1.39
     ed
    1.39
    POSITIVE LOGITS
    udiantes
    2.24
    fnamefont
    2.23
     uomo
    2.16
    <unused1652>
    2.14
     Wildcats
    2.14
    <unused1167>
    2.13
     auxqu
    2.09
     यूज्ड
    2.08
     Centres
    2.05
     वीं
    2.05
    Activations Density 0.179%

    No Known Activations