© 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. 84878
    Prev
    Next
    INDEX
    Explanations

    looking like

    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
    mektedir
    -1.10
    跚
    -1.05
     및
    -1.05
    Obtain
    -1.00
    にて
    -0.98
     Obtain
    -0.96
    ճ
    -0.95
    rater
    -0.94
     VARIOUS
    -0.94
     rámci
    -0.94
    POSITIVE LOGITS
    特に
    1.13
     really
    1.09
     now
    1.02
    ơm
    1.01
     consequences
    1.01
     называ
    1.00
     szczególnie
    0.99
     scared
    0.92
     особенно
    0.91
     intValue
    0.91
    Activations Density 0.007%

    No Known Activations