© 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. 34-GEMMASCOPE-RES-131K
    7. 57205
    Prev
    Next
    INDEX
    Explanations

    page description

    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_34/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
    死
    -0.75
     死
    -0.75
    缀
    -0.74
     Monmouth
    -0.72
    acijos
    -0.71
    Награ
    -0.70
    
    -0.69
    瑁
    -0.69
    tuj
    -0.69
    Km
    -0.68
    POSITIVE LOGITS
    efficient
    0.71
    オイ
    0.65
     evolution
    0.65
    CURY
    0.64
     efficient
    0.63
    labs
    0.61
    log
    0.61
    Modific
    0.60
     amid
    0.60
    ow
    0.60
    Activations Density 0.052%

    No Known Activations