© 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. 58532
    Prev
    Next
    INDEX
    Explanations

    Mac, iPhone, Linux, SWT

    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
     hoạt
    -0.81
    潜在
    -0.80
     holen
    -0.78
     Melo
    -0.74
     offending
    -0.73
    lytes
    -0.72
     escenarios
    -0.71
     paralelo
    -0.71
     fría
    -0.71
    diad
    -0.71
    POSITIVE LOGITS
    niczy
    0.84
     RATIO
    0.80
     Assays
    0.79
     Quince
    0.79
    urbed
    0.77
     Tym
    0.76
    werve
    0.75
    Dichloroethene
    0.75
    いか
    0.73
     finit
    0.72
    Activations Density 0.001%

    No Known Activations