© 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. 221699
    Prev
    Next
    INDEX
    Explanations

    rational articulation

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

    managing carefully

    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
    晔
    0.47
    닉
    0.41
    确认
    0.41
     souh
    0.41
    க்கிய
    0.40
    凶
    0.40
    鬢
    0.40
    峯
    0.39
    Domin
    0.39
     Calle
    0.39
    POSITIVE LOGITS
     Balkans
    0.54
     اعمال
    0.45
     Blockchain
    0.45
     اید
    0.44
     articulation
    0.44
     direita
    0.43
     ايضا
    0.43
     rational
    0.43
     protop
    0.43
     LGBT
    0.42
    Activations Density 0.001%

    No Known Activations