© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2485
    Prev
    Next
    INDEX
    Explanations

    digits 0-9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    <unused1837>
    1.08
    ‰
    1.08
    க்கு
    1.05
     возможности
    1.02
    <unused273>
    1.00
     علي
    0.99
     이를
    0.97
     비
    0.97
    <unused544>
    0.96
    ؕ
    0.95
    POSITIVE LOGITS
    0
    1.73
    1
    1.44
    3
    1.40
    4
    1.35
    2
    1.33
    5
    1.33
    6
    1.27
    7
    1.27
    8
    1.10
    9
    1.07
    Activations Density 0.099%

    No Known Activations