© 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. 73480
    Prev
    Next
    INDEX
    Explanations

    fisher and related words

    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
     albero
    -0.88
    凩
    -0.85
    KLE
    -0.84
    的海
    -0.81
    MARIA
    -0.81
    UNGE
    -0.81
     immaculate
    -0.79
     США
    -0.79
     waarschijnlijk
    -0.79
     abito
    -0.79
    POSITIVE LOGITS
    زي
    0.91
    づらい
    0.89
     حيات
    0.85
     IRELAND
    0.84
    indexPath
    0.81
    nac
    0.81
    folk
    0.81
    tagHelper
    0.80
    然而
    0.79
    PRICE
    0.77
    Activations Density 0.024%

    No Known Activations