© 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. 34-GEMMASCOPE-RES-131K
    4. 110419
    Prev
    Next
    INDEX
    Explanations

    connected or disconnected states

    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_34/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
     English
    -0.85
    総合
    -0.75
    ⋀
    -0.73
    Respondents
    -0.71
    Weigh
    -0.71
     barbarous
    -0.70
     була
    -0.67
    イルド
    -0.67
     سرم
    -0.66
    を楽しむ
    -0.65
    POSITIVE LOGITS
     connected
    2.39
     Connected
    2.31
    Connected
    2.09
    connected
    2.03
    CONNECTED
    1.95
    连
    1.55
     connectivity
    1.50
     disconnected
    1.47
     连
    1.46
     CONNECT
    1.45
    Activations Density 0.032%

    No Known Activations