© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75289
    Prev
    Next
    INDEX
    Explanations

    describing content detail

    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
    حاب
    0.50
    Profession
    0.47
    好处
    0.45
    లలో
    0.44
    恫
    0.43
     profes
    0.42
    美容
    0.42
     vardı
    0.41
     swept
    0.41
    一样的
    0.41
    POSITIVE LOGITS
    confident
    0.56
     молоды
    0.48
    한
    0.47
     มาก
    0.46
    ্তে
    0.46
     சாத
    0.45
    થે
    0.44
     गिनी
    0.44
    sampling
    0.44
    ปี
    0.43
    Activations Density 0.001%

    No Known Activations