© 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. 53089
    Prev
    Next
    INDEX
    Explanations

    and interests

    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
     domic
    0.51
    niger
    0.48
     ін
    0.47
    銹
    0.47
    Nigeria
    0.46
     niger
    0.45
     contributory
    0.45
     appreciable
    0.45
     altru
    0.44
     въ
    0.43
    POSITIVE LOGITS
    வார்கள்
    0.54
     Baek
    0.54
     خیلی
    0.50
    萨
    0.50
     Masaki
    0.50
    这
    0.48
     அழகான
    0.48
     Thermodynamics
    0.47
    垫
    0.47
    🧸
    0.47
    Activations Density 0.005%

    No Known Activations