© 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. 113142
    Prev
    Next
    INDEX
    Explanations

    previous limits, sick days, band score

    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
     way
    0.54
     estable
    0.49
     estabele
    0.48
    Established
    0.48
     doua
    0.48
     secure
    0.47
    า
    0.46
    튼
    0.46
    ী
    0.46
     dễ
    0.46
    POSITIVE LOGITS
     Selenium
    0.47
     Sensors
    0.45
    zones
    0.44
    zioni
    0.43
    selt
    0.43
    vii
    0.41
    鍘
    0.41
     Parmi
    0.40
    nsic
    0.40
    的話
    0.40
    Activations Density 0.010%

    No Known Activations