© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109228
    Prev
    Next
    INDEX
    Explanations

    user defined

    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
    Lunes
    -1.04
     coarsely
    -0.89
    ケモン
    -0.88
    כד
    -0.85
     এর
    -0.84
    Brunswick
    -0.83
    ficha
    -0.83
    簡単な
    -0.83
    Hermoso
    -0.80
    Ofic
    -0.79
    POSITIVE LOGITS
     defined
    2.20
    defined
    2.05
    Defined
    1.91
     Defined
    1.66
    define
    1.50
    DEFIN
    1.40
    Define
    1.36
     défin
    1.30
     definida
    1.30
     definido
    1.29
    Activations Density 0.052%

    No Known Activations