© 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. 51872
    Prev
    Next
    INDEX
    Explanations

    communication for

    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
    postion
    0.52
    positioned
    0.48
    ਾਰ
    0.47
    nutí
    0.45
     séquence
    0.45
    偵
    0.44
    termine
    0.42
     मास्टर
    0.42
     prostitute
    0.42
    춥
    0.42
    POSITIVE LOGITS
     \%
    0.52
     z
    0.51
     iç
    0.49
    _)
    0.46
    সমস্ত
    0.46
     wasn
    0.45
    \%
    0.45
    いた
    0.45
    ycz
    0.45
     bền
    0.44
    Activations Density 0.005%

    No Known Activations