© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5095
    Prev
    Next
    INDEX
    Explanations

    criticism of people and leaders

    np_acts-logits-general · gemini-2.5-flash-lite

    singlish and informal speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Remarkably
    0.48
     remarkable
    0.46
     विविध
    0.45
     সার্ব
    0.44
     remarkably
    0.44
     Spruce
    0.43
     plaid
    0.43
    }^{+\
    0.42
     pivotal
    0.41
     evidently
    0.41
    POSITIVE LOGITS
     nonsense
    0.67
     foolish
    0.62
    😂😂
    0.62
    nonsense
    0.61
     useless
    0.60
     thief
    0.60
     sabi
    0.59
     Buhari
    0.59
    🤣🤣
    0.59
     dey
    0.58
    Activations Density 0.070%

    No Known Activations