© 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. 47009
    Prev
    Next
    INDEX
    Explanations

    wine saver, wish, ideal, we, berries

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

    FOMO; Libras; peroxide; cut; vertically

    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
     différences
    0.51
     दस
    0.50
     விரை
    0.45
     complication
    0.45
    쑹
    0.45
     thousand
    0.43
     lím
    0.42
     три
    0.41
     хло
    0.41
     ثلاثة
    0.41
    POSITIVE LOGITS
    🛶
    0.52
    外科
    0.52
     aurait
    0.51
    ʿ
    0.48
     ग़
    0.47
    📞
    0.46
    ("",
    0.45
    (!
    0.45
    hook
    0.45
     auraient
    0.44
    Activations Density 0.000%

    No Known Activations