Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11647
    Prev
    Next
    INDEX
    Explanations

    epitaxial growth substrate

    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_22/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
    選手の
    -0.79
     opened
    -0.79
    いわゆる
    -0.77
     definidos
    -0.77
     attendees
    -0.76
     enrich
    -0.76
     anuales
    -0.76
     fuimos
    -0.76
     femininity
    -0.75
    Faux
    -0.74
    POSITIVE LOGITS
     raccomand
    0.91
     Segel
    0.91
    波
    0.91
    ਪ
    0.84
    zyst
    0.84
    ätigung
    0.83
    COUVER
    0.83
     McL
    0.83
     другая
    0.82
     pasir
    0.82
    Activations Density 0.146%

    No Known Activations