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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 3537
    Prev
    Next
    INDEX
    Explanations

    purchasing, disposable income

    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_53_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
    lensFlare
    0.46
     Dependencies
    0.41
    รก
    0.41
     keySchedule
    0.41
     መንገድ
    0.40
    徇
    0.39
     Interactions
    0.39
     operazioni
    0.39
    诽
    0.38
    干扰
    0.38
    POSITIVE LOGITS
     purchasing
    1.88
     Purchasing
    1.71
     disposable
    1.53
     buying
    1.39
     Disposable
    1.32
    Purch
    1.31
    purch
    1.28
     PURCH
    1.27
    Disposable
    1.23
     Buying
    1.22
    Activations Density 0.035%

    No Known Activations