© 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. 1647
    Prev
    Next
    INDEX
    Explanations

    positions of responsibility

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

    It detects mentions of professional roles and job titles (e.g., CEO, VP, Managing Director, Dungeon Master, Marketing Coordinator, principal).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
     automakers
    0.44
     ultraf
    0.43
     π
    0.42
     usamos
    0.42
     its
    0.41
    ങ്ങളാണ്
    0.40
     hydraz
    0.40
     usar
    0.40
     bytes
    0.40
     apoptosis
    0.40
    POSITIVE LOGITS
    වර
    0.70
    を務
    0.70
     responsabile
    0.57
    দের
    0.55
     Duties
    0.54
    兼
    0.53
    Duties
    0.50
     coordinator
    0.50
     responsável
    0.49
     कर्तव्यों
    0.49
    Activations Density 0.146%

    No Known Activations