© 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. 58590
    Prev
    Next
    INDEX
    Explanations

    prim, prima, prime

    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
    侗
    -0.78
    uckle
    -0.77
    vatten
    -0.77
     Atten
    -0.75
    Atten
    -0.74
    分
    -0.74
     выполнять
    -0.74
     τρό
    -0.74
    acke
    -0.73
    דש
    -0.72
    POSITIVE LOGITS
     facie
    1.24
     prima
    0.98
    Prima
    0.98
    prima
    0.95
     prim
    0.93
     Prima
    0.91
    arily
    0.89
     преми
    0.89
    rose
    0.87
     Prim
    0.84
    Activations Density 0.016%

    No Known Activations