© 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. 90022
    Prev
    Next
    INDEX
    Explanations

    introducing alternatives

    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
    éndose
    -1.77
     também
    -1.73
     trám
    -1.73
    蔸
    -1.71
     órganos
    -1.60
     также
    -1.59
     этом
    -1.59
    romeda
    -1.55
    
    -1.54
     остальные
    -1.52
    POSITIVE LOGITS
     if
    2.89
     alternatively
    2.75
     simply
    2.63
     else
    2.44
     just
    2.44
     even
    2.41
     conversely
    2.20
     наоборот
    1.92
     perhaps
    1.91
     If
    1.80
    Activations Density 0.063%

    No Known Activations