© 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. 52968
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    Მ
    0.39
    iscal
    0.39
    ilik
    0.38
    ham
    0.38
    bane
    0.38
     સ્પ
    0.38
    
    0.37
    ifie
    0.37
    ifier
    0.37
    ạ
    0.36
    POSITIVE LOGITS
     представители
    0.40
    ंख्य
    0.38
    خستان
    0.37
     ряд
    0.36
    VO
    0.36
    DAO
    0.36
     Consiglio
    0.36
     Missouri
    0.35
     Fare
    0.35
     الفرنس
    0.35
    Activations Density 0.034%

    No Known Activations