© 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. 37423
    Prev
    Next
    INDEX
    Explanations

    amenities within places

    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
    orgen
    0.40
    ብ
    0.39
     trend
    0.39
     street
    0.38
    েনি
    0.38
     boulevard
    0.38
     динами
    0.38
     Lieblings
    0.38
    ො
    0.38
     stroll
    0.37
    POSITIVE LOGITS
     benches
    0.66
     places
    0.53
     bench
    0.52
     tables
    0.51
     seats
    0.50
     chairs
    0.49
    seats
    0.47
     machines
    0.47
     toilets
    0.47
     desks
    0.46
    Activations Density 0.004%

    No Known Activations