© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 238824
    Prev
    Next
    INDEX
    Explanations

    ergonomic handle, monitor usage, trap beats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bijoux
    0.55
     blah
    0.55
     trainee
    0.47
     \
    0.47
     dure
    0.47
     spontaneous
    0.46
     Widget
    0.46
     vit
    0.46
     mewah
    0.46
     synapse
    0.45
    POSITIVE LOGITS
    assertions
    0.50
     компонентов
    0.46
    తిక
    0.46
    coroutines
    0.44
     selectors
    0.44
    োপাধ্যায়
    0.43
    ସ
    0.43
     components
    0.43
    miques
    0.43
    Christine
    0.43
    Activations Density 0.004%

    No Known Activations