© 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. 196627
    Prev
    Next
    INDEX
    Explanations

    dates or structured lists

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

    formal addresses and procedures

    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
     Shreve
    0.50
    𝐾
    0.47
    ্সা
    0.46
    ルート
    0.45
    ワン
    0.45
     মাত্রা
    0.45
    Nr
    0.44
    セキュリティ
    0.44
     Baillargeon
    0.44
    ]^{-
    0.44
    POSITIVE LOGITS
     is
    0.57
     intestine
    0.48
    т
    0.47
     dold
    0.46
     fecal
    0.45
     merciless
    0.45
     punish
    0.44
     glist
    0.44
     henne
    0.44
    t
    0.44
    Activations Density 0.001%

    No Known Activations