© 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. 18257
    Prev
    Next
    INDEX
    Explanations

    character roles and what to play

    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
    atorul
    0.50
    Louis
    0.49
     Read
    0.49
    Political
    0.48
    ﻌ
    0.46
    Geo
    0.45
    Ş
    0.45
     आपत्ति
    0.45
    Baş
    0.45
    Transfer
    0.44
    POSITIVE LOGITS
    \
    0.50
    "</
    0.47
    方法
    0.43
     method
    0.43
     wiping
    0.42
     operativos
    0.42
     метод
    0.41
    واصل
    0.41
     замены
    0.41
    емый
    0.40
    Activations Density 0.005%

    No Known Activations