© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1400
    Prev
    Next
    INDEX
    Explanations

    grammatical corrections and

    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
    <unused49>
    0.98
     což
    0.98
     тобто
    0.96
    മം
    0.95
    <unused42>
    0.94
    usega
    0.86
    აში
    0.85
    ungnya
    0.85
     için
    0.83
     takže
    0.82
    POSITIVE LOGITS
     and
    5.41
    และ
    5.38
     và
    5.09
     और
    5.06
     и
    4.94
     आणि
    4.93
     및
    4.91
    和
    4.80
     ಮತ್ತು
    4.65
     மற்றும்
    4.63
    Activations Density 5.146%

    No Known Activations