© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41223
    Prev
    Next
    INDEX
    Explanations

    without losing

    np_acts-logits-general · gemini-2.5-flash-lite

    reduces or lowers stress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rn
    0.50
    গি
    0.50
     calles
    0.47
    Сан
    0.46
    NW
    0.46
    Đ
    0.46
    FEDERAL
    0.46
     lettere
    0.46
     leyenda
    0.45
     statunitense
    0.45
    POSITIVE LOGITS
    кола
    0.46
     أص
    0.44
     elog
    0.44
    明的
    0.44
     المرك
    0.43
     المقص
    0.43
     المشار
    0.43
    鸦
    0.43
    ريبي
    0.42
    ższe
    0.42
    Activations Density 0.001%

    No Known Activations