© 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. 46930
    Prev
    Next
    INDEX
    Explanations

    seized with, but no, to air

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

    okay, alright, then

    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
     กําลัง
    0.63
    ในสนาม
    0.59
     मुला
    0.55
     ሴ
    0.52
     {}>,
    0.52
     簡単
    0.50
     выпущен
    0.49
    ফর্ম
    0.49
     บน
    0.48
    िफिशियल
    0.48
    POSITIVE LOGITS
    t
    0.59
    Ham
    0.47
    DN
    0.46
    I
    0.46
    SEC
    0.44
    REG
    0.44
     Ham
    0.44
    Com
    0.44
    ük
    0.44
     I
    0.43
    Activations Density 0.000%

    No Known Activations