© 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. 20357
    Prev
    Next
    INDEX
    Explanations

    avoid personal information

    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
     Inoltre
    0.52
     estreno
    0.50
    吗
    0.49
    仡
    0.49
    ψη
    0.49
     fortemente
    0.48
     wyniki
    0.47
     instantaneously
    0.47
    焲
    0.47
     ভগবান
    0.46
    POSITIVE LOGITS
     newspaper
    0.55
     mail
    0.52
     members
    0.50
    0.50
    v
    0.50
     page
    0.49
    )
    0.48
    ,
    0.48
     ra
    0.47
    Page
    0.47
    Activations Density 0.027%

    No Known Activations