© 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. 13053
    Prev
    Next
    INDEX
    Explanations

    cycling and bikes

    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
    敔
    0.53
     متر
    0.46
     Tonawanda
    0.44
     सीटेट
    0.43
    烀
    0.42
    Firebase
    0.41
    🧸
    0.41
    <0xDB>
    0.41
     জনগোষ্ঠীর
    0.40
     Crowley
    0.40
    POSITIVE LOGITS
     cyclist
    1.00
     cycling
    0.96
     cyclists
    0.93
     bike
    0.91
     bikes
    0.88
    bike
    0.87
    Cycling
    0.87
     bicycle
    0.85
     Cycling
    0.84
     fiets
    0.81
    Activations Density 0.035%

    No Known Activations