© 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. 98198
    Prev
    Next
    INDEX
    Explanations

    sprite

    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
    明月
    -0.92
    куль
    -0.88
    ITURE
    -0.82
     Persian
    -0.81
     CQ
    -0.79
    atisfaction
    -0.78
     Unternehmen
    -0.78
     operaciones
    -0.77
     Anbieter
    -0.77
    riture
    -0.73
    POSITIVE LOGITS
     Sprite
    1.00
    Sprite
    0.97
     sprite
    0.96
     Spr
    0.91
     sprit
    0.91
    sprite
    0.86
     đáo
    0.81
    精灵
    0.81
     unacc
    0.79
     SPR
    0.78
    Activations Density 0.007%

    No Known Activations