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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 18842
    Prev
    Next
    INDEX
    Explanations

    formal conditions and definitions

    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
     модели
    0.99
     polytopes
    0.99
     polytope
    0.98
    <unused1741>
    0.98
     постара
    0.96
    ্তা
    0.95
     ইন্দু
    0.94
     ligands
    0.93
     integrals
    0.91
     алыңыз
    0.90
    POSITIVE LOGITS
     tom
    0.83
    ⎜
    0.78
    EOUT
    0.75
     قام
    0.75
    Tom
    0.73
    =
    0.72
     visit
    0.71
    phon
    0.67
    June
    0.66
    ذه
    0.66
    Activations Density 0.000%

    No Known Activations