© 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. 9628
    Prev
    Next
    INDEX
    Explanations

    amounts and quantities

    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
     Despite
    0.36
     Mga
    0.35
     Managed
    0.32
     T
    0.31
     quatro
    0.31
     versus
    0.31
    ‌های
    0.30
     permiten
    0.30
    们的
    0.30
     TensorFlow
    0.30
    POSITIVE LOGITS
    がたくさん
    0.35
     मोठे
    0.32
    <unused2138>
    0.31
    很多
    0.30
    <unused2125>
    0.30
    <unused2130>
    0.30
     ಅನೇಕ
    0.29
     often
    0.29
    <unused2197>
    0.29
     people
    0.29
    Activations Density 0.199%

    No Known Activations