© 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. 34-GEMMASCOPE-RES-131K
    4. 54255
    Prev
    Next
    INDEX
    Explanations

    HTTP request methods

    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
    sodik
    -0.89
    ragalactic
    -0.88
     Redondo
    -0.85
    不论
    -0.82
     mina
    -0.82
    گم
    -0.81
    onChangeText
    -0.79
    孩子们
    -0.79
    狗狗
    -0.79
     eterna
    -0.79
    POSITIVE LOGITS
     alojamiento
    0.93
     colorear
    0.92
     adquisición
    0.91
     diferentes
    0.90
    retirement
    0.89
    lastung
    0.89
     fön
    0.88
    igera
    0.87
    هذا
    0.86
     cordón
    0.85
    Activations Density 0.005%

    No Known Activations