© 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. 27209
    Prev
    Next
    INDEX
    Explanations

    concepts and actions

    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
    真正
    0.44
     ವಿಧಾನ
    0.43
     initi
    0.42
     BEGIN
    0.42
    的方式
    0.40
    䢌
    0.40
    䐈
    0.40
    gressive
    0.39
    藝術
    0.39
     നേര
    0.39
    POSITIVE LOGITS
    '
    0.46
     ngunit
    0.39
     affectionately
    0.38
     però
    0.37
     sandpaper
    0.36
     arsenic
    0.35
     dunno
    0.35
     शकते
    0.35
     dentures
    0.35
    apsack
    0.35
    Activations Density 0.008%

    No Known Activations