© 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. 222198
    Prev
    Next
    INDEX
    Explanations

    By chance

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

    "Kailasa" and specific punctuation

    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
    0.59
    6
    0.59
    /
    0.58
    7
    0.58
    -
    0.55
    4
    0.51
    8
    0.51
    5
    0.50
    تح
    0.48
    «
    0.47
    POSITIVE LOGITS
    ⇵
    0.61
    াপন্ন
    0.57
     adiab
    0.55
     आकाश
    0.53
     चौपट
    0.53
     தோட்டங்கள்
    0.50
     दरों
    0.50
     अराज
    0.50
     तरंग
    0.49
     पाओ
    0.49
    Activations Density 0.001%

    No Known Activations