© 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. 44930
    Prev
    Next
    INDEX
    Explanations

    go back, want to, tile cement, shelf faux

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

    verify again, instructions

    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
    editable
    0.55
    dominant
    0.51
    重点
    0.50
     activité
    0.48
    日常
    0.48
    ̻
    0.48
    lifetime
    0.48
    lear
    0.47
    online
    0.47
    avoro
    0.47
    POSITIVE LOGITS
    ň
    0.46
     Pru
    0.46
     Silver
    0.45
     जहाज
    0.44
     Пусть
    0.43
     आर्क
    0.42
     бла
    0.42
     mö
    0.41
     пусть
    0.41
    Norm
    0.41
    Activations Density 0.000%

    No Known Activations