© 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. 12424
    Prev
    Next
    INDEX
    Explanations

    followed by a number

    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
    hwar
    -0.87
     corris
    -0.86
    男人
    -0.84
    ociação
    -0.82
     Вікіпе
    -0.81
    might
    -0.81
     ballo
    -0.81
     começa
    -0.81
    may
    -0.80
    confirm
    -0.80
    POSITIVE LOGITS
    Jungkook
    0.91
     JUST
    0.89
    ptonshire
    0.86
    したのが
    0.84
     roche
    0.83
     ALWAYS
    0.83
    境的
    0.82
    ས།
    0.82
    raborty
    0.82
    じた
    0.81
    Activations Density 0.001%

    No Known Activations