© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132512
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite

    Seal, requirements, driven, platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝘾
    0.57
    𝑭
    0.57
    Б
    0.56
    𝙀
    0.54
    𝙴
    0.52
    С
    0.51
    𝙲
    0.50
    𝘴
    0.49
    𝙾
    0.48
    Опера
    0.48
    POSITIVE LOGITS
    valu
    0.48
    回答
    0.47
     offert
    0.45
     unchallenged
    0.43
    垠
    0.43
     inequ
    0.43
     intrans
    0.42
     undist
    0.41
    സ്സ
    0.41
    ൽ
    0.41
    Activations Density 0.000%

    No Known Activations