© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11214
    Prev
    Next
    INDEX
    Explanations

    real estate and residential property

    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
    本机
    0.47
     Wochschr
    0.46
    遍历
    0.45
    锉
    0.44
     प्रधाना
    0.44
     Inhibition
    0.43
    erequisite
    0.43
    酶
    0.43
     रिवीजन
    0.42
    进攻
    0.42
    POSITIVE LOGITS
     apartments
    1.59
     apartment
    1.51
     residential
    1.51
     Residences
    1.46
     Apartments
    1.45
     condo
    1.44
     condos
    1.42
     condominium
    1.41
     residences
    1.38
     condominiums
    1.38
    Activations Density 0.011%

    No Known Activations