© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4953
    Prev
    Next
    INDEX
    Explanations

    people and societal roles

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

    entities and categories

    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
    ’,
    0.50
    -,
    0.46
     owes
    0.46
    েরই
    0.45
    ',
    0.45
    ’.
    0.44
    .',
    0.43
     কর্তৃক
    0.43
    /',
    0.41
     kanssa
    0.41
    POSITIVE LOGITS
    的值
    0.47
     musically
    0.45
    的人物
    0.44
     personally
    0.43
     regarding
    0.42
     psyche
    0.42
    及其
    0.41
    ัด
    0.41
     Wür
    0.41
     adipisicing
    0.40
    Activations Density 0.052%

    No Known Activations