© 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. 103585
    Prev
    Next
    INDEX
    Explanations

    Today, How, Ruth

    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
     polymerization
    -0.79
    valente
    -0.78
     potret
    -0.76
    viewDid
    -0.74
    comfortable
    -0.74
    operazione
    -0.74
     vediamo
    -0.73
     দেখ
    -0.72
    érée
    -0.72
    dafri
    -0.71
    POSITIVE LOGITS
     Mr
    0.96
    Mr
    0.76
     Feier
    0.76
     premise
    0.75
    ✆
    0.74
     chaîne
    0.74
    HP
    0.73
     Violence
    0.73
    >|</
    0.73
     constituents
    0.72
    Activations Density 0.006%

    No Known Activations