© 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. 218772
    Prev
    Next
    INDEX
    Explanations

    ancestry test, laboratory assays

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

    result processing

    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
     lawan
    0.46
    ለያ
    0.46
    ELEASE
    0.45
     kalangan
    0.42
    akos
    0.41
     Meks
    0.41
    趴
    0.41
     YA
    0.40
     বিচ্ছিন্ন
    0.40
     संवेदनशील
    0.40
    POSITIVE LOGITS
    지난
    0.52
    Dor
    0.52
     czasie
    0.49
    пу
    0.48
    DAR
    0.47
    meg
    0.46
    Dd
    0.46
    Nuestro
    0.46
    дона
    0.44
    шку
    0.43
    Activations Density 0.000%

    No Known Activations