© 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. 8069
    Prev
    Next
    INDEX
    Explanations

    attendance and absences

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

    absence and attendance

    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
    固
    0.40
     modulating
    0.40
     accret
    0.39
     価格
    0.38
    ונה
    0.38
    μος
    0.37
    ิญ
    0.37
     carcinogenesis
    0.37
     વિચાર
    0.36
    簫
    0.36
    POSITIVE LOGITS
     attendance
    2.63
     Attendance
    2.61
    Attendance
    2.52
    attendance
    2.48
     absenteeism
    2.30
     absences
    2.17
     Absent
    1.95
    Absent
    1.90
     absent
    1.87
     absentee
    1.84
    Activations Density 0.071%

    No Known Activations