© 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. 212934
    Prev
    Next
    INDEX
    Explanations

    or Benef

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

    letter of acceptance

    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
    ικά
    0.52
    パラメータ
    0.52
    בה
    0.52
    ハ
    0.49
    バー
    0.48
     belirli
    0.48
     tervez
    0.47
     ঘনত্ব
    0.47
    ヴ
    0.47
    毎週
    0.47
    POSITIVE LOGITS
     alumna
    0.56
     astonished
    0.49
     conducted
    0.44
     doctora
    0.43
     underwent
    0.43
     Alumni
    0.42
     Eastman
    0.42
     WordPerfect
    0.42
     encamin
    0.42
     Remarkably
    0.42
    Activations Density 0.000%

    No Known Activations