© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7628
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ized
    1.07
    ppa
    1.05
    +}\
    1.05
    gris
    1.05
    halb
    1.04
    irs
    1.03
     Advisors
    1.03
    ത്തില
    1.02
    裱
    1.02
    oke
    1.02
    POSITIVE LOGITS
    ا
    1.65
    ר
    1.25
    an
    1.25
    ا۔
    1.19
    на
    1.17
    ம்பரிய
    1.17
    त
    1.14
    а
    1.13
    o
    1.12
    此之外
    1.09
    Activations Density 0.001%

    No Known Activations