© 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. 53-GEMMASCOPE-2-RES-262K
    7. 8075
    Prev
    Next
    INDEX
    Explanations

    addition and conjunction phrases

    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_53_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
     WITHIN
    0.27
    raison
    0.26
     tomto
    0.24
    ≐
    0.24
    每一次
    0.24
    nelle
    0.24
    뜻
    0.23
     মধ্যেই
    0.23
     OTHERWISE
    0.22
    儼
    0.22
    POSITIVE LOGITS
     Tand
    0.28
     tandem
    0.27
     conjunction
    0.26
     tand
    0.24
     considera
    0.24
    cii
    0.23
    agn
    0.23
    tand
    0.23
     depth
    0.22
    iciary
    0.22
    Activations Density 0.123%

    No Known Activations