© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 248664
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     руках
    0.55
    owne
    0.54
     अब्
    0.51
     ثاني
    0.51
    lll
    0.50
     그럼
    0.50
    cp
    0.49
     싶
    0.49
     fists
    0.49
    quí
    0.48
    POSITIVE LOGITS
     robotic
    0.46
     utama
    0.45
    AR
    0.43
     linearized
    0.43
     gamb
    0.42
     spiral
    0.41
     robotics
    0.41
     amounts
    0.41
     wolf
    0.41
     aromat
    0.40
    Activations Density 0.001%

    No Known Activations