© 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. 111672
    Prev
    Next
    INDEX
    Explanations

    code inclusion comments

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

    decorative separator lines made of repeated equal signs or dashes in code comments.

    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
     '
    -2.33
    ...'
    -1.69
    芣
    -1.65
     Hundreds
    -1.63
    をつけて
    -1.56
     There
    -1.53
    殆
    -1.50
     що
    -1.48
     Allgemeinen
    -1.47
     Many
    -1.44
    POSITIVE LOGITS
    จะ
    1.95
     importanti
    1.90
    1.80
    some
    1.76
     if
    1.74
    if
    1.74
    to
    1.74
    mathrm
    1.72
    鞮
    1.64
     predecessors
    1.61
    Activations Density 0.033%

    No Known Activations