© 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. 91150
    Prev
    Next
    INDEX
    Explanations

    the word on

    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
    recognize
    -0.85
    confusion
    -0.85
    problema
    -0.84
    参赛
    -0.84
    implicitly
    -0.84
    newest
    -0.83
     originalen
    -0.83
    市场的
    -0.82
    sugges
    -0.82
    欤
    -0.79
    POSITIVE LOGITS
     top
    0.85
    asis
    0.84
    phrag
    0.76
    RENDER
    0.75
    hetamine
    0.75
    igs
    0.75
     dưới
    0.75
    steroids
    0.74
    repeat
    0.74
     and
    0.74
    Activations Density 0.049%

    No Known Activations