© 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-262K
    7. 126243
    Prev
    Next
    INDEX
    Explanations

    agent interaction or representation

    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
    Lai
    0.50
    Orden
    0.39
    ţa
    0.39
    披
    0.38
    ్యం
    0.38
    Pss
    0.38
    дото
    0.38
    vet
    0.38
    tena
    0.38
     활
    0.37
    POSITIVE LOGITS
     особы
    0.52
    جهزة
    0.49
    iconductor
    0.47
     excelentes
    0.46
     считаю
    0.46
     bitOp
    0.45
     microl
    0.45
    椷
    0.45
     consacré
    0.44
    convolve
    0.44
    Activations Density 0.018%

    No Known Activations