© 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-65K
    7. 6386
    Prev
    Next
    INDEX
    Explanations

    asking for context

    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_65k_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
    Typical
    0.82
    typical
    0.82
    Если
    0.76
     **
    0.76
    what
    0.73
    **
    0.73
    verbal
    0.72
    ↵↵
    0.71
    have
    0.70
    Yeah
    0.69
    POSITIVE LOGITS
    .“
    0.97
     cuffs
    0.88
    保証
    0.88
     tiers
    0.87
     Khanna
    0.85
     clinics
    0.85
    .”)
    0.84
     mani
    0.84
    的不
    0.83
     bekl
    0.82
    Activations Density 0.013%

    No Known Activations