© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228449
    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
    кци
    0.49
     vecchio
    0.48
     בעי
    0.45
     vattum
    0.45
     pozwoli
    0.43
    võ
    0.43
    🕑
    0.43
     pieno
    0.42
     Complaints
    0.42
    Соцмережа
    0.42
    POSITIVE LOGITS
     http
    0.40
     privileges
    0.39
    ification
    0.39
    ieft
    0.38
    ogs
    0.37
     entrusted
    0.37
    某
    0.36
     /
    0.36
     सुविधाएं
    0.36
    ingale
    0.36
    Activations Density 0.006%

    No Known Activations