© 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. 4310
    Prev
    Next
    INDEX
    Explanations

    stages, phases, steps, lines

    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
    Combination
    0.69
    tbody
    0.68
     Kelas
    0.68
    Quem
    0.67
     suatu
    0.65
    culares
    0.65
    Combine
    0.64
    們
    0.64
    snippets
    0.63
     ły
    0.62
    POSITIVE LOGITS
     অর্থাৎ
    1.10
     onwards
    1.08
    ของการ
    0.95
     अर्थात
    0.91
    에서는
    0.90
    の内容
    0.90
    以降
    0.89
     onward
    0.85
    에서의
    0.84
    에는
    0.83
    Activations Density 0.317%

    No Known Activations