© 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. 91541
    Prev
    Next
    INDEX
    Explanations

    again another

    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
     všetky
    -0.92
     každé
    -0.83
    unu
    -0.80
     parça
    -0.80
     telephone
    -0.80
     každého
    -0.77
     wszystkie
    -0.76
    ♉
    -0.75
     Telephone
    -0.75
    xeb
    -0.75
    POSITIVE LOGITS
    今度は
    1.37
     again
    1.34
     Again
    1.24
     another
    1.21
    こちらも
    1.19
     ANOTHER
    1.18
    again
    1.16
    Again
    1.13
    อีก
    1.13
     erneut
    1.11
    Activations Density 0.039%

    No Known Activations