© 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-65K
    7. 8083
    Prev
    Next
    INDEX
    Explanations

    many specific entities

    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_65k_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
     benutzt
    0.92
     von
    0.89
     dimana
    0.88
     länger
    0.87
     binnen
    0.87
    ende
    0.85
    ä
    0.85
    า
    0.85
    ö
    0.85
     innerhalb
    0.84
    POSITIVE LOGITS
    许多
    1.13
     innumerable
    0.95
     painstaking
    0.95
     numerosos
    0.94
     numerosas
    0.94
     многочис
    0.92
     numerous
    0.92
     individually
    0.91
    <unused360>
    0.91
     countless
    0.90
    Activations Density 0.006%

    No Known Activations