© 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-65K
    7. 15577
    Prev
    Next
    INDEX
    Explanations

    describing attributes and qualifiers

    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
    獧
    0.44
    ス
    0.44
     cuerpo
    0.43
    zc
    0.42
    剡
    0.42
    sG
    0.41
    ensión
    0.41
    crc
    0.41
     contend
    0.40
    ্বস্ত
    0.40
    POSITIVE LOGITS
     imaginative
    0.44
     Кита
    0.39
     importation
    0.39
     stunts
    0.39
     Shanghai
    0.39
    밉
    0.38
     outsourcing
    0.38
    冤
    0.38
     москов
    0.38
     innovative
    0.38
    Activations Density 0.000%

    No Known Activations