© 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. 83200
    Prev
    Next
    INDEX
    Explanations

    most typical scenario

    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
     escuch
    0.42
     akár
    0.41
    بر
    0.41
    沨
    0.41
     Vás
    0.41
    ुरा
    0.40
    膂
    0.40
     escucha
    0.40
     cortos
    0.39
     staring
    0.39
    POSITIVE LOGITS
     posteriorly
    0.47
     PRES
    0.45
     밝
    0.44
     נישט
    0.43
    
    0.43
     posterior
    0.41
     넓
    0.40
     な
    0.40
     没有
    0.39
     центром
    0.39
    Activations Density 0.011%

    No Known Activations