© 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. 50489
    Prev
    Next
    INDEX
    Explanations

    words ending in able

    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
     POSSIBLE
    -0.98
     formules
    -0.95
     possibles
    -0.93
     Allergy
    -0.90
    aled
    -0.90
     andare
    -0.86
     福袋
    -0.86
    strual
    -0.86
    ▬▬
    -0.85
    gner
    -0.85
    POSITIVE LOGITS
    ﾅ
    0.93
    ūras
    0.93
    ละเอ
    0.92
     throughout
    0.91
    blum
    0.91
    否
    0.90
    صورة
    0.89
    钤
    0.89
    幹線
    0.89
    ࣪
    0.89
    Activations Density 0.056%

    No Known Activations