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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109395
    Prev
    Next
    INDEX
    Explanations

    Japanese patent application or society

    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
     DESK
    -0.97
     hẹn
    -0.82
     ریزی
    -0.81
     wies
    -0.79
     ℃
    -0.77
     ника
    -0.77
     familial
    -0.76
    뭄
    -0.74
     LEON
    -0.74
     ROGER
    -0.73
    POSITIVE LOGITS
     thác
    0.82
    会员
    0.79
     стал
    0.78
    Membership
    0.77
     membership
    0.77
    води
    0.77
     so
    0.77
     just
    0.75
     Membership
    0.73
     describes
    0.71
    Activations Density 0.032%

    No Known Activations