© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    Quebec H3A 0G4

    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
    a
    1.55
    нің
    1.43
    ра
    1.39
    e
    1.38
    مبر
    1.36
    alista
    1.34
    ി
    1.33
    мни
    1.32
    ۰
    1.31
    alang
    1.31
    POSITIVE LOGITS
    ਿਆਂ
    1.74
    __);
    1.69
    𝐲
    1.69
    𝐨
    1.60
    𝐞
    1.57
     सुकून
    1.55
    textAlign
    1.52
    𝐢
    1.51
    𝐡
    1.50
    ielsen
    1.50
    Activations Density 0.046%

    No Known Activations