© 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. 14069
    Prev
    Next
    INDEX
    Explanations

    Photon

    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
     informed
    0.38
     informing
    0.38
    ⺀
    0.37
    头的
    0.37
     mingled
    0.37
    %+
    0.36
     धैर्य
    0.36
     Đầu
    0.36
    頭
    0.36
     Lounge
    0.35
    POSITIVE LOGITS
     Photon
    0.42
     photon
    0.39
    뎌
    0.39
    وبت
    0.38
    ovable
    0.38
    Agr
    0.38
    镛
    0.37
    photon
    0.37
    ridos
    0.36
    Optional
    0.36
    Activations Density 0.017%

    No Known Activations