© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5827
    Prev
    Next
    INDEX
    Explanations

    cors and parsing

    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
    ือ
    0.40
    ֹ
    0.40
    زى
    0.39
    において
    0.39
    ãs
    0.39
    위
    0.38
    funded
    0.38
    ОО
    0.37
    Funding
    0.37
    缁
    0.37
    POSITIVE LOGITS
     smelling
    0.42
     হোটেলে
    0.42
     invigor
    0.41
     sweaty
    0.40
     worn
    0.39
    queur
    0.39
    origine
    0.39
    attaque
    0.38
    edo
    0.38
     smelly
    0.38
    Activations Density 0.008%

    No Known Activations