© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19199
    Prev
    Next
    INDEX
    Explanations

    varying formality, length, and complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    value
    0.31
    result
    0.28
    frame
    0.28
    response
    0.27
    》。
    0.27
    ™.
    0.27
    したり
    0.26
    。
    0.26
    ge
    0.26
    previous
    0.26
    POSITIVE LOGITS
     bahwa
    0.33
     médicos
    0.32
     تھی
    0.31
     paket
    0.29
     و
    0.29
     tasas
    0.29
     thyroid
    0.28
     şunu
    0.28
     médical
    0.28
     मेडिकल
    0.28
    Activations Density 0.062%

    No Known Activations