© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43916
    Prev
    Next
    INDEX
    Explanations

    explaining certain concepts or ideas

    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
    ਿਆਂ
    0.46
     đị
    0.44
    ব
    0.43
    вими
    0.42
    ルコ
    0.42
    ष्ण
    0.42
     besieged
    0.41
     バック
    0.41
     seguenti
    0.41
    ียน
    0.41
    POSITIVE LOGITS
    ory
    0.45
    }}{
    0.43
     отсутствие
    0.42
    偶尔
    0.41
    ierry
    0.40
    eres
    0.40
     occasional
    0.40
     ocas
    0.40
    out
    0.39
    ่
    0.39
    Activations Density 0.001%

    No Known Activations