© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10663
    Prev
    Next
    INDEX
    Explanations

    python 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_9_width_262k_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
    St
    0.87
    Cursor
    0.82
    Vlad
    0.80
    彼
    0.78
    memset
    0.77
    iciones
    0.75
    speakers
    0.72
    এছ
    0.70
    Sistema
    0.70
    ྕ
    0.70
    POSITIVE LOGITS
     lawfully
    1.05
     safely
    1.03
     goodness
    0.95
     heme
    0.92
     cahaya
    0.92
     soprav
    0.91
     Jehová
    0.91
     começ
    0.90
     waktu
    0.90
    ು
    0.90
    Activations Density 0.151%

    No Known Activations