© 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. 10-GEMMASCOPE-RES-131K
    7. 7393
    Prev
    Next
    INDEX
    Explanations

    comments and code

    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
     گزینه
    -1.12
    伤感
    -1.02
     economic
    -1.02
     afectados
    -1.00
     Electricity
    -1.00
     involucrados
    -1.00
     those
    -1.00
        
    -1.00
     –
    -0.99
    綜合報導
    -0.99
    POSITIVE LOGITS
    essment
    1.66
    ();*/
    1.48
    givings
    1.40
    annten
    1.38
    titial
    1.33
    ämä
    1.32
    hoppers
    1.31
    itieren
    1.30
    mittedly
    1.30
    fielder
    1.29
    Activations Density 0.041%

    No Known Activations