© 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. 11944
    Prev
    Next
    INDEX
    Explanations

    python script execution

    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
    under
    1.36
     usually
    1.18
    ometimes
    1.13
    ­
    1.13
    in
    1.10
    ავლ
    1.09
     necessary
    1.09
     bound
    1.09
     sometimes
    1.08
    on
    1.08
    POSITIVE LOGITS
     dando
    2.37
    <unused1422>
    2.32
     мальчика
    2.27
    ꪽ
    2.24
    <unused1386>
    2.23
     venced
    2.23
    <unused1306>
    2.21
     samoglas
    2.20
     iniziare
    2.17
     sungai
    2.17
    Activations Density 0.139%

    No Known Activations