© 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. 103834
    Prev
    Next
    INDEX
    Explanations

    secrets and their context

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

    the phrase "secrets of" or variations like "secret of/to" followed by something being revealed or explained.

    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
     erroneous
    -1.65
    閙
    -1.59
     jugend
    -1.58
    lägg
    -1.57
     tanques
    -1.55
    ܊
    -1.55
    低下
    -1.54
    ,''
    -1.50
    deja
    -1.49
    狃
    -1.49
    POSITIVE LOGITS
     about
    1.97
    場合
    1.92
     that
    1.80
    pa
    1.69
     pérd
    1.65
    q
    1.63
    man
    1.63
    O
    1.59
     単
    1.59
    gan
    1.56
    Activations Density 0.014%

    No Known Activations