© 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. 22-GEMMASCOPE-RES-131K
    4. 67515
    Prev
    Next
    INDEX
    Explanations

    numbers followed by commas or specific keywords

    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_22/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
    tbx
    -1.00
     to
    -0.99
     potranno
    -0.98
    faccia
    -0.98
     until
    -0.96
     câteva
    -0.94
     Briefe
    -0.92
    以來
    -0.90
     VTT
    -0.89
     while
    -0.88
    POSITIVE LOGITS
    1.09
    ikum
    1.05
     atribu
    0.99
     arreg
    0.98
    ге
    0.98
    视着
    0.98
     але
    0.96
    стройки
    0.94
     маши
    0.93
     kropp
    0.92
    Activations Density 0.011%

    No Known Activations