© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33412
    Prev
    Next
    INDEX
    Explanations

    genetic diversity, to complete

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

    mathematical notation and symbols within academic text, particularly in equations and formulas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tionary
    -0.88
     rationale
    -0.84
     между
    -0.82
     poussière
    -0.82
     Archivado
    -0.82
     Nhưng
    -0.81
    Тарих
    -0.81
     mayoría
    -0.81
    zus
    -0.81
     如果
    -0.80
    POSITIVE LOGITS
     telo
    0.99
     itong
    0.88
     tricot
    0.86
     estúdio
    0.85
    了一口
    0.85
    ]=>
    0.84
     only
    0.82
    が登場
    0.82
     coming
    0.81
    克斯
    0.81
    Activations Density 0.008%

    No Known Activations