© 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. 10-GEMMASCOPE-RES-131K
    7. 111650
    Prev
    Next
    INDEX
    Explanations

    implementation followed by identifiers

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

    the `@implementation` keyword in Objective-C source code files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    🢒
    -1.98
    鸰
    -1.98
     "
    -1.85
    ヤン
    -1.76
    ！"
    -1.75
    內容簡介
    -1.70
     作り方
    -1.60
    identes
    -1.58
     was
    -1.57
     توسط
    -1.55
    POSITIVE LOGITS
    0
    2.13
    ”.
    2.11
    ”,
    2.03
    ”)
    2.03
    ”:
    1.88
    ”),
    1.86
    ”).
    1.84
    ’)
    1.77
    ”،
    1.76
    可能会
    1.72
    Activations Density 0.006%

    No Known Activations