© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77293
    Prev
    Next
    INDEX
    Explanations

    desorption/ionization

    np_acts-logits-general · gemini-2.5-flash-lite

    hyphenated compound terms where the words are connected with a dash.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ยนต์
    -0.92
    だよ
    -0.81
    alisation
    -0.78
    Failure
    -0.77
    hedral
    -0.76
    ystemen
    -0.73
    burgo
    -0.73
     MyBatis
    -0.73
    ignment
    -0.73
     endoscopic
    -0.71
    POSITIVE LOGITS
    兼
    1.01
     songwriter
    1.01
    \/
    0.95
    slash
    0.93
     cum
    0.91
    /
    0.89
     slash
    0.85
    ⁄
    0.81
     صفح
    0.79
    ciato
    0.78
    Activations Density 0.219%

    No Known Activations