© 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. 1712
    Prev
    Next
    INDEX
    Explanations

    Liu, Joseph, Lewis, STAR

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

    generate text

    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
    ောင့်
    0.42
     εκεί
    0.42
    呯
    0.42
    sberg
    0.40
     Nghi
    0.40
    སྐ
    0.40
     சிறந்த
    0.39
    берг
    0.39
    এই
    0.38
     змі
    0.38
    POSITIVE LOGITS
     刘
    0.48
    Liu
    0.47
    Joseph
    0.47
     Joseph
    0.44
    Star
    0.43
     Liu
    0.43
    STAR
    0.42
     Lewis
    0.42
    収入
    0.42
    ević
    0.41
    Activations Density 0.166%

    No Known Activations