© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5860
    Prev
    Next
    INDEX
    Explanations

    As of today, November

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Tres
    0.72
    CLASSI
    0.68
     returnMe
    0.68
    <unused1722>
    0.66
     খাজ
    0.65
    callbacks
    0.65
     Tues
    0.65
    점에
    0.64
    ovíd
    0.64
     
    0.64
    POSITIVE LOGITS
    0.84
    aran
    0.72
     arm
    0.65
     ge
    0.65
     liter
    0.65
     grup
    0.65
     indywidual
    0.62
    وڑ
    0.61
    हास
    0.61
    óp
    0.61
    Activations Density 0.049%

    No Known Activations