© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61009
    Prev
    Next
    INDEX
    Explanations

    names or titles

    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_10/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
     cubanos
    -1.01
    experiments
    -1.01
    bathroom
    -0.98
    waterproof
    -0.96
    larıyla
    -0.96
    ţele
    -0.94
    ☎
    -0.94
     ruidos
    -0.93
     reprez
    -0.92
     tanque
    -0.92
    POSITIVE LOGITS
    Would
    1.00
    1
    0.93
     только
    0.92
    would
    0.91
     فقط
    0.86
    མ
    0.85
     democrat
    0.85
    гота
    0.85
    ця
    0.85
    сами
    0.84
    Activations Density 0.000%

    No Known Activations