© 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. 181606
    Prev
    Next
    INDEX
    Explanations

    performance, protest, screening, opportunities, youth

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

    physical descriptions

    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
     standaard
    0.48
    inent
    0.45
     somit
    0.45
    ား
    0.43
     centrifuged
    0.43
     поступи
    0.43
    шель
    0.43
    ಔ
    0.43
    measured
    0.42
    schaft
    0.42
    POSITIVE LOGITS
     युवक
    0.55
     Opportunities
    0.48
     युवकों
    0.48
     روی
    0.47
     drips
    0.47
     앞에
    0.46
     Strategy
    0.45
     Youth
    0.45
    ंबे
    0.45
     bruises
    0.44
    Activations Density 0.000%

    No Known Activations