© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14375
    Prev
    Next
    INDEX
    Explanations

    Saint and effects

    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
    icolor
    -1.00
     Obtén
    -0.98
    arrón
    -0.96
    viamo
    -0.95
     Μαρ
    -0.95
     Selecciona
    -0.92
    dchen
    -0.91
     Ofrece
    -0.91
    IndentedString
    -0.90
     Deiner
    -0.89
    POSITIVE LOGITS
    ),
    0.98
    ;
    0.91
     turístico
    0.81
     周年
    0.77
     trouverez
    0.77
     keseluruhan
    0.75
    ❃
    0.75
     dukungan
    0.75
    вные
    0.72
     verrez
    0.72
    Activations Density 0.013%

    No Known Activations