© 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. 121998
    Prev
    Next
    INDEX
    Explanations

    accommodation or former book

    np_acts-logits-general · gemini-2.5-flash-lite

    aerodynamics and flight

    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
     blasts
    0.51
     résident
    0.49
     articulating
    0.47
    카
    0.47
     confirmations
    0.46
    드
    0.46
     continues
    0.46
     sights
    0.46
    /
    0.45
    די
    0.44
    POSITIVE LOGITS
     меся
    0.55
     شود
    0.51
     மாய
    0.51
     цель
    0.48
     прош
    0.48
     ढूं
    0.48
     வாழ்க்க
    0.47
     зло
    0.47
     неизвест
    0.47
     मैक
    0.46
    Activations Density 0.001%

    No Known Activations