© 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. 1444
    Prev
    Next
    INDEX
    Explanations

    "I" express preferences or actions

    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
     fulfilment
    0.47
     яви
    0.45
    InvalidArgument
    0.44
     فرمایا
    0.42
    擔任
    0.42
     geldig
    0.42
    ENGLISH
    0.42
    謁
    0.42
     fulfils
    0.42
     Gandhiji
    0.41
    POSITIVE LOGITS
     prefer
    0.98
     recomend
    0.81
     upgraded
    0.80
     replaced
    0.78
     purchased
    0.77
     bought
    0.75
     Prefer
    0.73
     prefers
    0.73
     replace
    0.71
     installed
    0.70
    Activations Density 0.463%

    No Known Activations