© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250877
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мүм
    0.41
     veya
    0.40
     hypothetical
    0.40
     YouTube
    0.39
     или
    0.39
    ’).
    0.39
     reembolso
    0.38
     ç
    0.38
     gluten
    0.37
     gerente
    0.37
    POSITIVE LOGITS
    ISource
    0.48
    གྲ
    0.47
     Հ
    0.46
    Nonnull
    0.46
    Sehr
    0.44
     পরবর্ত
    0.44
    Mutability
    0.44
     Primarily
    0.44
    Nota
    0.42
    Foi
    0.42
    Activations Density 0.003%

    No Known Activations