© 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. 38907
    Prev
    Next
    INDEX
    Explanations

    best quality

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     frequentemente
    -3.41
    罴
    -3.28
    ፨
    -3.06
    驺
    -2.81
    鏷
    -2.75
     altamente
    -2.73
    𝄆
    -2.72
    獴
    -2.67
    垟
    -2.64
    
    -2.59
    POSITIVE LOGITS
    Some
    3.09
    Almost
    2.72
    Several
    2.64
    鉆
    2.61
     Almost
    2.59
    Even
    2.53
    which
    2.45
    Although
    2.42
    While
    2.41
    just
    2.38
    Activations Density 0.029%

    No Known Activations