© 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. 12689
    Prev
    Next
    INDEX
    Explanations

    appeal to

    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
    ies
    2.49
    <bos>
    2.30
    offs
    2.22
    IE
    2.17
     room
    2.16
    osing
    2.14
    <code>
    2.11
    ಯ
    2.07
    ind
    2.05
    ie
    2.02
    POSITIVE LOGITS
    鈿
    3.21
     живело
    3.13
    지털
    3.01
    ępow
    2.99
    eOut
    2.85
     hija
    2.84
    ्रल
    2.83
    भाविक
    2.79
    ција
    2.75
     nbfs
    2.74
    Activations Density 0.003%

    No Known Activations