© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13956
    Prev
    Next
    INDEX
    Explanations

    than four / examples started

    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
    ي
    3.65
     depred
    3.08
    ಿ
    3.08
     кушымта
    3.04
     cracking
    2.93
    ্ম
    2.93
    istiques
    2.93
    ాము
    2.90
    瘡
    2.89
    ackBar
    2.88
    POSITIVE LOGITS
    <i>
    2.19
    ionate
    2.13
    plan
    1.97
    aren
    1.94
    ß
    1.90
    else
    1.89
    <bos>
    1.81
    ·
    1.77
     S
    1.75
    ben
    1.71
    Activations Density 0.018%

    No Known Activations