© 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. 8333
    Prev
    Next
    INDEX
    Explanations

    real estate features

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

    property features

    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
     offerings
    0.42
    更为
    0.42
    常规
    0.40
     அவ்வ
    0.40
    Via
    0.39
    瞧
    0.39
    Read
    0.39
     Bennett
    0.39
     delineation
    0.39
     &'
    0.38
    POSITIVE LOGITS
     swimming
    0.70
     fenced
    0.67
    游泳
    0.66
     balconies
    0.65
     balcony
    0.64
     gated
    0.64
     gyms
    0.63
     jacuzzi
    0.63
     balkon
    0.63
     parking
    0.62
    Activations Density 0.124%

    No Known Activations