© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31124
    Prev
    Next
    INDEX
    Explanations

    reduced, stop, specialized, deliberate, focused

    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
     তাহাই
    0.46
    キュリティ
    0.44
    Emojis
    0.44
    鞦
    0.44
     готовы
    0.44
     Glaub
    0.43
    oteurs
    0.43
     Brooks
    0.43
    кле
    0.43
    ⌔
    0.43
    POSITIVE LOGITS
     on
    0.55
     section
    0.49
     roughness
    0.46
     level
    0.46
     texture
    0.45
     industrial
    0.45
     supplier
    0.45
     submarine
    0.45
     obvious
    0.43
     request
    0.43
    Activations Density 0.013%

    No Known Activations