© 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. 2244
    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
    การ
    0.57
    3
    0.56
    di
    0.55
    du
    0.49
     TRE
    0.47
    dt
    0.47
    ↵↵
    0.46
     cenu
    0.46
    doi
    0.46
    gu
    0.46
    POSITIVE LOGITS
     Comanche
    0.50
    MVCProject
    0.48
    ෲ
    0.48
     //#
    0.46
     vulve
    0.46
     validType
    0.45
    чиго
    0.45
    getSource
    0.45
    ajati
    0.45
     اين
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.