© 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. 38488
    Prev
    Next
    INDEX
    Explanations

    sci-fi cinema

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

    vulnerabilities, Royal History

    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
    insol
    0.50
    il
    0.49
    avic
    0.48
    н
    0.47
    у
    0.47
     показатель
    0.46
    мей
    0.45
    er
    0.45
    ant
    0.45
    ova
    0.45
    POSITIVE LOGITS
     puisi
    0.58
     gerakan
    0.53
     syair
    0.51
    🎣
    0.51
     persegi
    0.50
     ayam
    0.50
     throat
    0.48
     segala
    0.48
     perjalanan
    0.48
     egalitarian
    0.48
    Activations Density 0.000%

    No Known Activations