© 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. 92528
    Prev
    Next
    INDEX
    Explanations

    error or boundary 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
    tdown
    -0.74
    HELL
    -0.73
     vives
    -0.72
    
    -0.71
     denomina
    -0.71
     کمک
    -0.66
     combinação
    -0.66
     đối
    -0.66
    parti
    -0.65
    ួ
    -0.64
    POSITIVE LOGITS
    observers
    0.77
     liked
    0.68
    ortic
    0.67
     kriminal
    0.67
     tenían
    0.66
    Sib
    0.66
     Horv
    0.66
    比べ
    0.65
     hb
    0.65
     Links
    0.65
    Activations Density 0.052%

    No Known Activations