© 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. 3594
    Prev
    Next
    INDEX
    Explanations

    code, macros, and commands

    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
    वाती
    0.38
    Rusty
    0.37
    彘
    0.35
    嘍
    0.34
    牙
    0.34
     przys
    0.33
    Zeneca
    0.33
    ксана
    0.33
    చ్చు
    0.32
    フォルト
    0.32
    POSITIVE LOGITS
     simplemente
    0.49
     semplicemente
    0.48
     $=$
    0.45
     jednostavno
    0.45
     označ
    0.43
     означает
    0.43
     simply
    0.41
     ifades
    0.40
    ્સ
    0.39
    通过
    0.39
    Activations Density 0.022%

    No Known Activations