© 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. 8513
    Prev
    Next
    INDEX
    Explanations

    at api

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

    hacking and camping tips

    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
    ↵
    0.57
      
    0.55
     NUE
    0.54
    íj
    0.54
    '
    0.52
    наче
    0.52
     ת
    0.49
     QUE
    0.48
    朗
    0.48
     הת
    0.48
    POSITIVE LOGITS
     semisimple
    0.64
     fermion
    0.55
     phosphorylated
    0.55
     symplect
    0.55
    golang
    0.54
     enthal
    0.53
    وسیع
    0.53
     নিষ্ঠ
    0.53
     درون
    0.52
     dissipative
    0.52
    Activations Density 0.000%

    No Known Activations