© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14837
    Prev
    Next
    INDEX
    Explanations

    layers and levels

    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
     އ
    0.47
    ង
    0.47
    पाउंड
    0.46
    ﻪ
    0.45
    ми
    0.45
     ပဲ
    0.45
    ຼ
    0.44
    ﺲ
    0.44
    Pointing
    0.44
     ಪೂರ್ವ
    0.43
    POSITIVE LOGITS
     layers
    0.79
    层
    0.77
     layer
    0.73
    ชั้น
    0.71
     level
    0.70
    層
    0.70
    层次
    0.68
     tầng
    0.65
    층
    0.63
     слоя
    0.63
    Activations Density 0.080%

    No Known Activations