© 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. 10771
    Prev
    Next
    INDEX
    Explanations

    extensible

    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
    amette
    2.66
    ब्दिक
    2.61
    ون
    2.34
    یت
    2.34
    ⊱
    2.29
    ndash
    2.25
    cheiden
    2.21
    ونَ
    2.14
    stwo
    2.14
    adır
    2.13
    POSITIVE LOGITS
    racellular
    2.89
     substring
    2.65
     SQLException
    2.59
    ᄍ
    2.49
     requestCode
    2.48
    ত্রিম
    2.48
    ᇁ
    2.47
    รรม
    2.47
    uzione
    2.46
    CEED
    2.44
    Activations Density 0.009%

    No Known Activations