© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14578
    Prev
    Next
    INDEX
    Explanations

    tumor markers

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

    file extensions in web development contexts, particularly JavaScript and CSS file references.

    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_10/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
    ӧ
    -1.59
     when
    -1.56
     The
    -1.52
    ttes
    -1.36
    											
    -1.34
     Heft
    -1.34
     because
    -1.32
     if
    -1.32
     beginnen
    -1.31
    計畫
    -1.29
    POSITIVE LOGITS
     and
    1.83
    และ
    1.72
     土産
    1.70
    หรือ
    1.64
     including
    1.59
     Kleidung
    1.59
     chaleureux
    1.55
    雠
    1.53
    elerik
    1.52
     사람
    1.50
    Activations Density 0.010%

    No Known Activations