© 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. 247087
    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
    s
    0.70
    er
    0.55
    ум
    0.49
    :
    0.47
    Books
    0.46
    ty
    0.46
    F
    0.46
    ун
    0.45
    um
    0.44
    ्
    0.44
    POSITIVE LOGITS
     indicó
    0.47
     .(
    0.46
     campes
    0.44
     docente
    0.44
     debacle
    0.44
     clinique
    0.44
     nisid
    0.44
     mediterr
    0.43
     españa
    0.43
     inglese
    0.43
    Activations Density 0.002%

    No Known Activations