© 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. 40-GEMMASCOPE-2-RES-262K
    7. 5356
    Prev
    Next
    INDEX
    Explanations

    order shipping status

    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_40_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
     endogenous
    0.41
     diurnal
    0.40
     oscillatory
    0.40
     unexplored
    0.40
     drows
    0.39
     جامع
    0.39
    謁
    0.39
    場面
    0.37
     cohom
    0.36
     hypertrophy
    0.36
    POSITIVE LOGITS
     shipping
    2.20
     shipped
    2.08
     shipment
    2.06
    Shipping
    2.00
     Shipping
    1.94
    shipping
    1.93
     shipments
    1.92
     Shipment
    1.72
     SHIPPING
    1.71
    発送
    1.60
    Activations Density 0.025%

    No Known Activations