© 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. 17519
    Prev
    Next
    INDEX
    Explanations

    door, DoorDash, doorbell, hinge

    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
     двер
    0.56
     door
    0.53
     doors
    0.53
     дверей
    0.52
    дій
    0.51
     двери
    0.48
    鐏
    0.47
    дні
    0.46
    Accessibility
    0.46
     mobilise
    0.46
    POSITIVE LOGITS
    ways
    0.57
    way
    0.50
    steps
    0.48
    leading
    0.44
    槛
    0.43
    ivering
    0.42
    ningar
    0.42
    ismillahirrah
    0.42
    ort
    0.41
    np
    0.41
    Activations Density 0.007%

    No Known Activations