© 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. 59810
    Prev
    Next
    INDEX
    Explanations

    strength, server, ocean, lift, flow, error, journal, evening

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

    bootstrap samples

    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
     siphon
    0.48
    kak
    0.47
    noh
    0.46
    دود
    0.43
    elernt
    0.42
    Ultimately
    0.41
    Suff
    0.41
    鈿
    0.41
    OIL
    0.41
    ЕС
    0.41
    POSITIVE LOGITS
     grudge
    0.46
    ških
    0.45
     pregunt
    0.43
     โอ้
    0.43
     বলিতে
    0.42
     aparat
    0.42
    បង្ហាញ
    0.42
    一边
    0.42
     relevante
    0.41
     utwor
    0.41
    Activations Density 0.001%

    No Known Activations