© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    additional

    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
    ী
    2.26
     appren
    1.96
    ъ
    1.87
    ayos
    1.79
     оба
    1.75
    Formatted
    1.72
    endimento
    1.69
    ยอม
    1.69
    é
    1.66
     οποία
    1.63
    POSITIVE LOGITS
    gris
    3.04
    ה
    2.86
    captcha
    2.38
    ानिस्तान
    2.34
     nmea
    2.33
    hnt
    2.27
    grained
    2.24
    ⁸
    2.23
     પડશે
    2.22
     لل
    2.18
    Activations Density 0.037%

    No Known Activations