© 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. 10715
    Prev
    Next
    INDEX
    Explanations

    actions and in-speech descriptions

    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
     obeyed
    0.44
     grinning
    0.43
     whim
    0.43
     blushing
    0.43
     terrified
    0.41
     sobbing
    0.40
     obey
    0.39
    喊
    0.38
     uttering
    0.38
     obeying
    0.38
    POSITIVE LOGITS
     emphasizes
    0.39
     desks
    0.38
     examples
    0.38
     संघर्ष
    0.37
     emphasize
    0.36
     argue
    0.36
     producers
    0.35
    sailboat
    0.35
     convivial
    0.35
     HVAC
    0.35
    Activations Density 0.053%

    No Known Activations