© 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. 203629
    Prev
    Next
    INDEX
    Explanations

    paid by

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

    controlling Spain, who blinked, we often

    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
     потому
    0.55
     persuade
    0.50
     despise
    0.50
     constru
    0.50
    }$\\
    0.49
     impractical
    0.49
     मुकद
    0.49
    🤭
    0.48
    $-$,
    0.48
     पाएगा
    0.48
    POSITIVE LOGITS
     Belgi
    0.52
     først
    0.50
     Aachen
    0.45
    server
    0.45
    rating
    0.45
    ink
    0.44
     Breton
    0.44
    source
    0.42
    颚
    0.42
    isation
    0.42
    Activations Density 0.000%

    No Known Activations