© 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. 7538
    Prev
    Next
    INDEX
    Explanations

    home improvement contractors

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

    home repair and contracting services

    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
    ртуа
    0.52
     anuv
    0.52
    ݢ
    0.49
     estudia
    0.49
     pedagogical
    0.46
     多い
    0.46
    MovementControls
    0.46
     APIDC
    0.46
     身
    0.45
     endowed
    0.45
    POSITIVE LOGITS
     homeowners
    1.74
     homeowner
    1.73
     contractor
    1.30
     contractors
    1.27
     Contractor
    1.21
     Contractors
    1.20
     handyman
    1.19
     installers
    1.08
    施工
    1.07
     Roofing
    1.07
    Activations Density 0.731%

    No Known Activations