© 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. 10-GEMMASCOPE-RES-131K
    7. 67277
    Prev
    Next
    INDEX
    Explanations

    clinical predictors

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

    C++ iterator operations and method calls like begin(), end(), and data().

    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_10/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
     also
    -2.06
     también
    -1.76
     dimenti
    -1.60
    他にも
    -1.52
     was
    -1.51
     också
    -1.48
     тоже
    -1.47
     too
    -1.45
    y
    -1.45
     также
    -1.41
    POSITIVE LOGITS
     Seventy
    1.39
     včetně
    1.22
     استناد
    1.21
    姈
    1.19
    Suara
    1.19
     wyłącznie
    1.18
     pouze
    1.17
     Eighty
    1.17
     ausschließlich
    1.16
    鹛
    1.15
    Activations Density 0.002%

    No Known Activations