© 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. 6080
    Prev
    Next
    INDEX
    Explanations

    file path and name extraction

    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
     துணை
    0.39
     કરવો
    0.39
     (/
    0.38
    વું
    0.37
     "-"]
    0.36
     "-",
    0.36
     andere
    0.36
     drugih
    0.36
     innego
    0.36
     '-':
    0.35
    POSITIVE LOGITS
     everyone
    0.41
    Everyone
    0.40
     সীমান্তে
    0.39
    Hotel
    0.39
    ᑐ
    0.38
     elderly
    0.38
    Multiple
    0.38
     jamais
    0.38
     полном
    0.38
     everybody
    0.38
    Activations Density 0.041%

    No Known Activations