© 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-65K
    7. 65208
    Prev
    Next
    INDEX
    Explanations

    need more, compound begins, delve into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    獨
    0.47
    arsipkan
    0.45
    υχ
    0.45
     እድ
    0.43
    兒童
    0.43
    恩
    0.43
    欽
    0.43
    觀察
    0.43
    學習
    0.42
     NOTES
    0.42
    POSITIVE LOGITS
     embedded
    0.44
     italiana
    0.42
     demod
    0.42
                        
    0.41
     spain
    0.41
     brutal
    0.40
                         
    0.40
     Ukraine
    0.38
     Forget
    0.38
    ?
    0.38
    Activations Density 0.004%

    No Known Activations