© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83879
    Prev
    Next
    INDEX
    Explanations

    rule, rules, conditions

    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
    භ
    -0.86
    Reservation
    -0.82
     METHODS
    -0.81
    歌唱
    -0.80
     asker
    -0.79
     tty
    -0.79
    >\<^
    -0.79
    vinfos
    -0.77
    FFER
    -0.76
     réserv
    -0.76
    POSITIVE LOGITS
     rule
    2.84
     rules
    2.69
    rule
    2.00
     Rules
    1.87
     conditions
    1.84
     Rule
    1.84
    Rule
    1.82
    规则
    1.77
    rules
    1.74
    Rules
    1.71
    Activations Density 0.077%

    No Known Activations