© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40504
    Prev
    Next
    INDEX
    Explanations

    shopping, dining, or entertainment

    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_31_width_65k_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
    }=\
    0.50
     precisam
    0.49
     vacanam
    0.48
     benötigt
    0.45
     Neces
    0.44
     necesit
    0.44
    ಟನೆ
    0.44
     അതിനാ
    0.43
     depresión
    0.42
     இருப்பதால்
    0.42
    POSITIVE LOGITS
    尊
    0.45
    RFID
    0.43
    Sport
    0.41
    Countryside
    0.40
    िलायंस
    0.40
    红色
    0.40
     націона
    0.39
     वहां
    0.38
    হু
    0.38
    环保
    0.38
    Activations Density 0.005%

    No Known Activations