© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3699
    Prev
    Next
    INDEX
    Explanations

    specific entities and details

    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
    면에
    0.68
    ة
    0.68
    咅
    0.68
    اب
    0.66
    subtree
    0.65
    আ
    0.64
    شت
    0.63
    й
    0.63
    ENIDO
    0.63
    ಲಯ
    0.62
    POSITIVE LOGITS
     orders
    0.70
     demographics
    0.64
     pools
    0.64
     outputPath
    0.62
     blister
    0.60
     often
    0.60
     identifies
    0.59
     predis
    0.59
     kelu
    0.59
     greens
    0.59
    Activations Density 0.002%

    No Known Activations