© 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. 54085
    Prev
    Next
    INDEX
    Explanations

    information following tags

    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
    FORD
    -0.97
    STONE
    -0.92
    ford
    -0.89
    RIAGE
    -0.88
     souvent
    -0.86
    __":
    -0.86
    тая
    -0.86
    "!
    -0.84
     religions
    -0.84
    ábor
    -0.84
    POSITIVE LOGITS
     current
    1.09
     estimated
    1.08
     currently
    1.05
     generated
    0.93
    current
    0.85
    InBackground
    0.82
     calculated
    0.79
     estimate
    0.78
    claimer
    0.77
    currentTime
    0.76
    Activations Density 0.032%

    No Known Activations