© 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. 7818
    Prev
    Next
    INDEX
    Explanations

    bear

    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
    ем
    1.29
    ет
    0.97
    eled
    0.95
    धारा
    0.87
    ется
    0.87
    ellä
    0.86
     remuneration
    0.86
    綵
    0.86
     rö
    0.84
    ेट
    0.84
    POSITIVE LOGITS
    beitung
    1.52
     bear
    1.41
     bears
    1.39
    bears
    1.35
    beiter
    1.34
    beiten
    1.30
    🐻
    1.27
     Bears
    1.27
     Bear
    1.26
     cubs
    1.18
    Activations Density 0.028%

    No Known Activations