© 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. 3155
    Prev
    Next
    INDEX
    Explanations

    update the

    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
    ून
    2.67
    ocuk
    2.40
    போன்ற
    2.30
    ្នាក់
    2.29
     ?”
    2.27
    PATHS
    2.27
    งาน
    2.21
    냄
    2.18
    __.
    2.16
    tedir
    2.15
    POSITIVE LOGITS
    вере
    2.59
    ﾞ
    2.57
    ו
    2.51
    ა
    2.46
    isieren
    2.44
    ikation
    2.44
    nements
    2.39
    یف
    2.38
    ঙ্গি
    2.36
    lccc
    2.36
    Activations Density 0.077%

    No Known Activations