© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12201
    Prev
    Next
    INDEX
    Explanations

    selecting UI elements or options

    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
    stylers
    -1.02
     ἐν
    -1.00
    ographer
    -0.99
    𝔰
    -0.97
    istische
    -0.96
     ὁ
    -0.96
    摂取
    -0.94
    ас
    -0.93
     Seven
    -0.92
     ἡ
    -0.91
    POSITIVE LOGITS
     select
    1.16
     selecting
    1.03
     beschik
    1.00
     seleccione
    0.98
     autocomplete
    0.98
    请选择
    0.96
    ֶּ
    0.95
    ૩
    0.95
     ネタバレ
    0.95
     selected
    0.94
    Activations Density 0.013%

    No Known Activations