© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 542
    Prev
    Next
    INDEX
    Explanations

    accessing array elements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     or
    -1.77
    相片
    -1.49
     any
    -1.45
    再加上
    -1.45
    璀
    -1.41
     may
    -1.40
    }{\
    -1.39
     does
    -1.38
    ólicos
    -1.37
    󠁿
    -1.32
    POSITIVE LOGITS
     this
    1.91
     kulinar
    1.78
     anhänger
    1.76
    bueno
    1.62
    也會
    1.57
    簠
    1.55
     indivíduos
    1.52
     komplette
    1.51
    september
    1.48
    maxn
    1.48
    Activations Density 0.027%

    No Known Activations