© 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. 71295
    Prev
    Next
    INDEX
    Explanations

    select or choose

    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
    などの
    -1.27
    heti
    -1.15
     они
    -1.13
    توضیحات
    -1.13
    それは
    -1.11
    齎
    -1.10
    achios
    -1.09
    ↵↵↵↵↵↵↵↵↵↵
    -1.07
     Milán
    -1.07
    但是在
    -1.05
    POSITIVE LOGITS
     chosen
    1.89
     chooses
    1.84
     choice
    1.73
     wisely
    1.61
     choices
    1.58
     selected
    1.57
     choose
    1.50
     a
    1.50
     among
    1.49
     chose
    1.49
    Activations Density 0.030%

    No Known Activations