© 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. 5785
    Prev
    Next
    INDEX
    Explanations

    lists and indicators

    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
     жүктөө
    0.47
    Ⲩ
    0.46
    Object
    0.45
     టిప్పు
    0.45
    Назад
    0.44
    в
    0.44
    Declared
    0.44
    伤
    0.44
    พันธ์
    0.41
    พันธุ์
    0.41
    POSITIVE LOGITS
     cups
    0.49
     taza
    0.49
    SIB
    0.45
     केली
    0.45
     किंवा
    0.45
     cataly
    0.44
     CBL
    0.44
     बीज
    0.43
     cabs
    0.42
    ést
    0.42
    Activations Density 0.005%

    No Known Activations