© 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. 146450
    Prev
    Next
    INDEX
    Explanations

    stamens, announcement, Mortar

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

    circular reasoning or infinite loops

    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
    рию
    0.41
    titleMargin
    0.41
     rightfully
    0.41
     specially
    0.40
    iril
    0.40
    ານ
    0.40
    有所
    0.39
    銥
    0.39
    ígen
    0.39
    ahlt
    0.39
    POSITIVE LOGITS
    ⚘
    0.48
     Sequences
    0.48
     annonce
    0.46
     দেখছি
    0.46
     era
    0.45
     بلا
    0.45
     necklaces
    0.44
     offer
    0.44
    ERA
    0.44
     stabile
    0.44
    Activations Density 0.003%

    No Known Activations