© 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. 10-GEMMASCOPE-RES-131K
    4. 70659
    Prev
    Next
    INDEX
    Explanations

    full version free download

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

    The neuron is detecting header‐style metadata for downloadable software—terms like “APK,” version or “Full Version,” “Free Download,” and similar package‐oriented headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Mengapa
    -1.73
    ;"></
    -1.56
    Kenapa
    -1.55
    Fitur
    -1.49
    Kelebihan
    -1.40
     differences
    -1.39
     industrias
    -1.39
     באתר
    -1.38
     также
    -1.37
     referencias
    -1.35
    POSITIVE LOGITS
    .
    1.23
     남자
    1.20
    Shouldn
    1.20
    Possibly
    1.16
     Remind
    1.13
     简介
    1.13
     joli
    1.09
     '':
    1.09
    wink
    1.09
    /
    1.09
    Activations Density 0.136%

    No Known Activations