© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30112
    Prev
    Next
    INDEX
    Explanations

    graduated from school

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.70
    Re
    0.65
     במהלך
    0.56
    ח
    0.55
    כ
    0.54
    로
    0.54
     għ
    0.53
    ﻨ
    0.52
     pounding
    0.52
     kanggo
    0.52
    POSITIVE LOGITS
     graduates
    0.67
    毕业生
    0.64
    phans
    0.62
    طان
    0.61
    畢業
    0.60
     졸업
    0.59
    urow
    0.59
     школ
    0.59
    schools
    0.57
     школы
    0.57
    Activations Density 0.005%

    No Known Activations