© 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. 3738
    Prev
    Next
    INDEX
    Explanations

    stable version or diffusion

    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
    鹉
    2.88
    hythmic
    2.86
     görsel
    2.82
    जनबी
    2.80
    বীন্দ্র
    2.67
    рёх
    2.65
    ы
    2.61
    𒌆
    2.60
    <unused2191>
    2.56
    <unused951>
    2.49
    POSITIVE LOGITS
    vans
    2.50
    out
    2.47
    dab
    2.16
    Com
    2.13
    en
    2.12
    ßer
    2.07
    con
    2.02
    H
    2.00
     En
    1.93
     padd
    1.92
    Activations Density 0.079%

    No Known Activations