© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 552
    Prev
    Next
    INDEX
    Explanations

    hydrodynamic formulation, equations, radii, conductance, shear

    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
    </i>
    -2.92
    ’
    -2.72
    :
    -2.70
    5
    -2.58
     et
    -2.38
     обслуживание
    -2.38
    1
    -2.27
    2
    -2.22
    7
    -2.22
    and
    -2.19
    POSITIVE LOGITS
    
    2.80
    縢
    2.77
     midst
    2.75
    鳢
    2.75
    螃
    2.72
    ⚌
    2.64
    鑁
    2.63
    衎
    2.61
     bytu
    2.59
    ༵
    2.59
    Activations Density 0.031%

    No Known Activations