© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 511
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     Newspapers
    0.93
     coincides
    0.90
    jsdel
    0.81
    acycline
    0.81
    ))=\
    0.80
    orrag
    0.80
     diar
    0.80
    }}=-\
    0.80
     sarkar
    0.77
    จัย
    0.76
    POSITIVE LOGITS
     Tipps
    2.51
     Anleitung
    2.41
     dicas
    2.32
     GUIDE
    2.32
     tips
    2.31
     Tips
    2.31
     HOW
    2.30
     how
    2.30
    examples
    2.28
     cómo
    2.26
    Activations Density 5.168%

    No Known Activations