© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7072
    Prev
    Next
    INDEX
    Explanations

    symmetric matrices and traversal

    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_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
     Están
    1.16
    GroupLayout
    1.15
     fossero
    1.13
    ت
    1.13
    BufOffset
    1.13
     washers
    1.12
    る
    1.12
    值
    1.11
     можливо
    1.11
     सीबीआई
    1.11
    POSITIVE LOGITS
    des
    1.06
    گری
    0.90
    ga
    0.89
    يب
    0.88
    Bag
    0.87
    Handsome
    0.84
    ella
    0.84
    Sample
    0.83
     esc
    0.82
    iga
    0.82
    Activations Density 0.000%

    No Known Activations