© 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. 17795
    Prev
    Next
    INDEX
    Explanations

    monthly subscriptions

    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
     elect
    0.37
    Җ
    0.37
     detention
    0.37
     Partially
    0.36
     لر
    0.36
     whor
    0.36
    rainfall
    0.36
     conjugate
    0.35
    浿
    0.35
     detain
    0.35
    POSITIVE LOGITS
    Front
    0.79
     Front
    0.76
    FRONT
    0.75
    front
    0.72
     FRONT
    0.68
     front
    0.66
    フロント
    0.60
     фрон
    0.59
     Frontiers
    0.59
     fronts
    0.55
    Activations Density 0.002%

    No Known Activations