© 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. 90864
    Prev
    Next
    INDEX
    Explanations

    anonymous guest access

    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
    แน่น
    -0.80
     לְ
    -0.76
     erbjuder
    -0.76
     insurgents
    -0.75
    味噌汁
    -0.75
    Haus
    -0.73
    สวย
    -0.71
     journaling
    -0.71
    Styled
    -0.71
    鬟
    -0.71
    POSITIVE LOGITS
     anonymous
    4.06
     guest
    3.80
     Anonymous
    3.66
    anonymous
    3.55
    Anonymous
    3.42
     Guest
    3.28
    Guest
    3.19
    guest
    3.17
     anon
    2.83
    anon
    2.67
    Activations Density 0.109%

    No Known Activations