© 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. 4242
    Prev
    Next
    INDEX
    Explanations

    facts classification

    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
    t
    0.91
     pickles
    0.87
     chandeliers
    0.81
     grapple
    0.78
     forecasts
    0.77
     Pickle
    0.77
     gloom
    0.77
    affected
    0.76
     pickled
    0.75
     dread
    0.75
    POSITIVE LOGITS
    जानकारी
    0.90
    𝐀
    0.89
     islam
    0.89
    Cuánt
    0.85
     वहीं
    0.85
     methodology
    0.85
     Achieving
    0.85
     metodología
    0.85
     samma
    0.84
    islam
    0.84
    Activations Density 0.000%

    No Known Activations