© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28317
    Prev
    Next
    INDEX
    Explanations

    formulas and calculations

    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_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
     impact
    0.43
    <0xE2>
    0.42
    ){
    0.41
     your
    0.40
     any
    0.38
     what
    0.38
     Cuba
    0.38
     Martha
    0.38
    সি
    0.38
     America
    0.38
    POSITIVE LOGITS
     одина
    0.46
    焲
    0.44
     മുഴുവ
    0.43
    三年
    0.41
    Wür
    0.41
    નારા
    0.41
    quefois
    0.41
    ᓂ
    0.41
     всех
    0.41
    䍘
    0.41
    Activations Density 0.004%

    No Known Activations