© 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. 52013
    Prev
    Next
    INDEX
    Explanations

    speed, downstream task, boolean

    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
    ITICAL
    0.47
    ިއ
    0.46
    乐观
    0.46
    ా
    0.46
     vaisse
    0.45
    ี้
    0.45
    帮助
    0.45
     kobi
    0.44
    Persistent
    0.43
    蓥
    0.43
    POSITIVE LOGITS
     brief
    0.46
     romantic
    0.46
     romant
    0.46
     machine
    0.43
     brie
    0.43
     auctioned
    0.41
     officially
    0.41
     starting
    0.40
     simplemente
    0.40
     divor
    0.40
    Activations Density 0.011%

    No Known Activations