© 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. 173635
    Prev
    Next
    INDEX
    Explanations

    former president

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

    leaves needing space

    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
    ियों
    0.52
     معنى
    0.50
     thiếu
    0.50
    য়নের
    0.49
    лин
    0.48
     پرویز
    0.47
    ه
    0.46
    리
    0.46
     finalizing
    0.46
    лан
    0.46
    POSITIVE LOGITS
    ssä
    0.50
     BOOL
    0.49
     AGA
    0.45
    essel
    0.45
    BERS
    0.45
    gers
    0.45
     Alguns
    0.44
    sterreich
    0.44
     harbours
    0.44
     SAR
    0.44
    Activations Density 0.001%

    No Known Activations