© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2287
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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_22_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
    ွက်
    0.65
    성
    0.64
     남
    0.60
     Wine
    0.60
    वक
    0.59
    疯
    0.58
    성의
    0.57
    驚
    0.57
    ချင်း
    0.57
     forte
    0.57
    POSITIVE LOGITS
     zero
    4.00
     Zero
    3.50
    zero
    3.48
     ZERO
    3.46
    Zero
    3.38
     zéro
    3.20
     cero
    3.15
    ZERO
    3.04
    ゼロ
    2.92
     zeros
    2.84
    Activations Density 0.831%

    No Known Activations