© 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. 108006
    Prev
    Next
    INDEX
    Explanations

    proper phrases or compound words

    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
     comté
    -1.16
     siè
    -1.02
     zarówno
    -1.02
    Mostly
    -1.00
    Chairman
    -1.00
     publicités
    -0.99
     både
    -0.98
    AfterViewInit
    -0.97
     تقوم
    -0.97
    Britain
    -0.97
    POSITIVE LOGITS
     definitively
    1.06
     insignificant
    1.05
     methodical
    1.03
     Jansen
    0.99
     tenacious
    0.98
     without
    0.98
     plunged
    0.97
     efficacious
    0.96
     prudent
    0.94
     marvellous
    0.93
    Activations Density 0.011%

    No Known Activations