© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    ـ
    1.20
    -
    1.18
    ـــ
    1.17
    ़
    1.15
    ̵
    1.15
    ַ
    1.13
     รวม
    1.08
     나
    1.07
     ​​
    1.06
    ــ
    1.05
    POSITIVE LOGITS
    the
    1.08
    county
    1.01
    has
    0.99
    based
    0.97
    سازی
    0.95
    contact
    0.93
    shirt
    0.93
    focused
    0.93
    group
    0.92
    and
    0.92
    Activations Density 0.504%

    No Known Activations