© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 2350
    Prev
    Next
    INDEX
    Explanations

    asking for tone and 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_16k_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
     *
    0.73
    ?"
    0.72
     what
    0.72
     arouse
    0.70
     `
    0.67
     au
    0.67
     দিয়েই
    0.66
    what
    0.65
     merciful
    0.60
     Amenities
    0.60
    POSITIVE LOGITS
     الشركات
    0.94
    .//
    0.92
     húmed
    0.86
    .])
    0.85
     bedrijven
    0.84
     اخرى
    0.83
     النقطه
    0.82
    ฏ
    0.82
     kanggo
    0.81
    În
    0.81
    Activations Density 0.031%

    No Known Activations