© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128467
    Prev
    Next
    INDEX
    Explanations

    increases and limits

    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_22/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
    ANTAGES
    -1.45
    Mejor
    -1.09
    Pacote
    -1.08
    Imagens
    -1.07
     conhece
    -1.07
    torie
    -1.05
     좋은
    -1.03
    💠
    -1.02
     contatto
    -1.02
     pensé
    -1.01
    POSITIVE LOGITS
     accommodated
    1.08
     by
    1.02
     accomod
    0.97
     Response
    0.93
    varer
    0.92
     Facility
    0.91
     under
    0.91
    ,
    0.88
    オリティ
    0.87
     adjust
    0.87
    Activations Density 0.071%

    No Known Activations