© 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-262K
    7. 17061
    Prev
    Next
    INDEX
    Explanations

    let's grip here

    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_262k_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
    éc
    0.53
    ée
    0.51
    i
    0.49
    cf
    0.48
    été
    0.47
    ę
    0.45
    ce
    0.44
    é
    0.44
     автомобиля
    0.43
    b
    0.43
    POSITIVE LOGITS
     stam
    0.50
     railing
    0.50
    ⏤
    0.50
     kaise
    0.50
     ทุก
    0.49
     kaun
    0.47
     foodie
    0.47
    ടാ
    0.46
     ingu
    0.46
    िरिक्स
    0.46
    Activations Density 0.002%

    No Known Activations