© 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. 94724
    Prev
    Next
    INDEX
    Explanations

    .com URLs and product links

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

    crucial, crucially, US government, COVID-19, Q3

    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
     eficaz
    0.43
     xxx
    0.42
     Aw
    0.42
    ımın
    0.40
     ayer
    0.40
    Aw
    0.39
     ṣ
    0.39
     якая
    0.39
    یوں
    0.38
     xx
    0.38
    POSITIVE LOGITS
     Kanton
    0.45
    čar
    0.45
     pourcentage
    0.44
    ⵅ
    0.43
    ப்பர்
    0.43
     recoup
    0.43
    šli
    0.42
    ראש
    0.42
     anúncios
    0.42
    ifer
    0.41
    Activations Density 0.002%

    No Known Activations