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

    Neuronpedia

    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. 47731
    Prev
    Next
    INDEX
    Explanations

    numbers and addition

    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
     habitat
    0.45
     variables
    0.44
     mugs
    0.42
     x
    0.41
     values
    0.41
     mug
    0.41
     what
    0.41
    ba
    0.41
     definitions
    0.40
     inequalities
    0.40
    POSITIVE LOGITS
     واپس
    0.48
    个月
    0.45
    审查
    0.42
    象征
    0.42
    łącznie
    0.41
    颁
    0.41
    威胁
    0.40
     deewana
    0.40
    协商
    0.40
    <unused52>
    0.39
    Activations Density 0.113%

    No Known Activations