© 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. 28897
    Prev
    Next
    INDEX
    Explanations

    URLs and structured data

    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
     angegeben
    0.34
     terminals
    0.31
     czyli
    0.31
     normales
    0.31
    And
    0.30
     bounds
    0.30
     lumea
    0.30
    ڱ
    0.30
    0
    0.29
     normale
    0.29
    POSITIVE LOGITS
     itemList
    0.32
     পুল
    0.30
     రాజకీయ
    0.30
     мульти
    0.29
     नेतृत्व
    0.29
     आयर
    0.29
     રાજ
    0.29
     चेन
    0.29
     जनजा
    0.29
     दस्ते
    0.29
    Activations Density 0.054%

    No Known Activations