© 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. 11396
    Prev
    Next
    INDEX
    Explanations

    path or direction

    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
     అనే
    0.71
     கரி
    0.69
    कौन
    0.68
     Envelope
    0.67
     பயன்படுத்த
    0.66
     يستخدم
    0.65
    ]],
    0.65
     ২
    0.63
     принял
    0.63
     کیا
    0.62
    POSITIVE LOGITS
     way
    3.20
    way
    2.56
    Way
    2.51
     Way
    2.45
     WAY
    2.35
    WAY
    2.09
     caminho
    1.70
     maneira
    1.57
     ways
    1.56
    方式
    1.55
    Activations Density 0.024%

    No Known Activations