© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17626
    Prev
    Next
    INDEX
    Explanations

    door step

    np_acts-logits-general · gemini-2.5-flash-lite

    door, knob, frame, DoorDash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doors
    0.86
    Doors
    0.79
    门
    0.77
     Doors
    0.70
    门的
    0.67
     portes
    0.66
     дверей
    0.66
    doors
    0.65
     door
    0.65
     cửa
    0.65
    POSITIVE LOGITS
     knob
    0.68
     jamb
    0.64
     knobs
    0.63
    槛
    0.62
    stopper
    0.60
    bells
    0.59
    frame
    0.57
    ills
    0.56
    檻
    0.56
     jams
    0.55
    Activations Density 0.027%

    No Known Activations