© 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. 71072
    Prev
    Next
    INDEX
    Explanations

    increasingly implementing notes

    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
    㿟
    0.48
    许多
    0.46
     обез
    0.45
    的人物
    0.45
    鳄
    0.45
     Rivals
    0.43
     FontFamily
    0.43
     Orc
    0.43
     بندی
    0.42
     Essentials
    0.42
    POSITIVE LOGITS
     decoded
    0.45
     decoder
    0.45
     decode
    0.44
     clockwise
    0.44
     diap
    0.43
     tanda
    0.43
    ᒎ
    0.43
    oltre
    0.42
     khi
    0.41
     nghệ
    0.40
    Activations Density 0.000%

    No Known Activations