© 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. 184062
    Prev
    Next
    INDEX
    Explanations

    security oftaking picturesfleet untiltradition callsfrom the

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

    obstacles and situations

    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
    ούς
    0.52
     Gött
    0.49
     Wirtschaft
    0.49
     logique
    0.48
    τι
    0.48
    ми
    0.46
    τί
    0.45
    懊
    0.44
    су
    0.44
     Maintenant
    0.43
    POSITIVE LOGITS
    ॔
    0.51
     ਮੰ
    0.50
    Travis
    0.48
     ねえ
    0.47
    ദം
    0.47
     bioavailability
    0.47
    फोर्स
    0.47
     स्तन
    0.46
     olma
    0.45
     예약
    0.45
    Activations Density 0.000%

    No Known Activations