© 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-262K
    7. 12287
    Prev
    Next
    INDEX
    Explanations

    Thailand, Finance, Srettha Thavisin

    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
    t
    2.43
    to
    2.17
    the
    1.95
    tion
    1.92
    tt
    1.90
    tr
    1.90
    ti
    1.89
    td
    1.88
    ט
    1.87
    ta
    1.82
    POSITIVE LOGITS
    chool
    2.11
    htein
    2.10
    ociety
    2.01
    phere
    2.01
    ̌
    2.00
    ourced
    1.99
    ymbol
    1.98
    atisf
    1.97
    ymptoms
    1.95
    aurus
    1.93
    Activations Density 0.437%

    No Known Activations