© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ේ
    0.55
     jamais
    0.51
    essayer
    0.48
     lorsque
    0.48
     luta
    0.46
     expérience
    0.45
    的地
    0.44
     ordinateur
    0.44
    DMA
    0.44
     cible
    0.44
    POSITIVE LOGITS
    ็น
    0.47
    FindingsResponse
    0.45
     favourably
    0.44
     المنتج
    0.44
    꼰
    0.44
    Invoke
    0.44
     straightforward
    0.43
    䣼
    0.43
    žev
    0.43
     शख
    0.43
    Activations Density 0.001%

    No Known Activations