© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64762
    Prev
    Next
    INDEX
    Explanations

    receiving, receipts, references

    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
     wonderful
    -0.76
    shadowOffset
    -0.72
    entieth
    -0.71
    ެ
    -0.70
    лору
    -0.70
     katkıda
    -0.66
     stanu
    -0.66
    霜
    -0.66
    corruption
    -0.66
     dealt
    -0.66
    POSITIVE LOGITS
    🔋
    0.75
    zeciw
    0.75
    村上
    0.75
    csak
    0.73
    MaxLength
    0.73
     ATTACK
    0.72
    Oktober
    0.71
    詡
    0.71
    rifugal
    0.70
    ᓚ
    0.69
    Activations Density 0.020%

    No Known Activations