© 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. 17-GEMMASCOPE-2-RES-16K
    7. 4753
    Prev
    Next
    INDEX
    Explanations

    rough estimates

    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
    Not in Any Lists

    No Comments

    Negative Logits
     promove
    0.98
     ಸಾಮಾನ್ಯವಾಗಿ
    0.94
     discounts
    0.91
    懈
    0.89
     criticize
    0.89
    後は
    0.89
    <unused328>
    0.89
    <unused1688>
    0.88
    gramModel
    0.88
    स्‍या
    0.87
    POSITIVE LOGITS
     AR
    0.86
     É
    0.76
    É
    0.73
     प
    0.73
    ball
    0.71
     AN
    0.71
    ép
    0.71
     é
    0.70
    AR
    0.69
    :
    0.67
    Activations Density 0.026%

    No Known Activations