© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134933
    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_40_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
    azes
    0.39
     characterised
    0.37
     архівів
    0.37
     собственных
    0.36
    耳
    0.36
     arqu
    0.35
    żs
    0.35
    туу
    0.35
    戞
    0.35
    lwjglVersion
    0.35
    POSITIVE LOGITS
     должны
    0.48
     deben
    0.45
     proven
    0.45
     parcel
    0.43
     բ
    0.42
    Proven
    0.41
     demostrar
    0.40
    proven
    0.40
    olactone
    0.40
     czynności
    0.40
    Activations Density 0.001%

    No Known Activations