© 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. 14158
    Prev
    Next
    INDEX
    Explanations

    themes: abstract concepts

    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
     đạt
    0.44
    苯
    0.43
     кі
    0.38
    Đặt
    0.38
    虽
    0.38
     उत्ते
    0.38
    )]=
    0.37
     nếu
    0.37
    实验室
    0.36
    )]
    0.36
    POSITIVE LOGITS
     everlasting
    0.47
     universality
    0.47
     Lof
    0.45
     eternal
    0.45
     timeless
    0.43
     photospheric
    0.42
     solidarity
    0.41
     perpetual
    0.41
    স্পতিবার
    0.41
     compassion
    0.41
    Activations Density 0.003%

    No Known Activations