© 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. 12343
    Prev
    Next
    INDEX
    Explanations

    after certain words

    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
     asshole
    0.42
     crappy
    0.41
    。
    0.40
     overkill
    0.37
     revolt
    0.37
     전부
    0.37
     merda
    0.37
     stupidity
    0.36
     falla
    0.36
     laziness
    0.36
    POSITIVE LOGITS
     discussions
    0.38
     interactions
    0.37
     with
    0.37
     thoughtfully
    0.37
     zarówno
    0.37
     нередко
    0.35
    <unused374>
    0.35
     interactive
    0.34
    ύ
    0.34
     concerning
    0.33
    Activations Density 0.306%

    No Known Activations