© 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. 36368
    Prev
    Next
    INDEX
    Explanations

    epub formatting with leading punctuation

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

    methamphetamine precursors

    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
     Rakh
    0.43
    ﺀ
    0.42
     Whatsapp
    0.39
     Ayuntamiento
    0.37
     økonom
    0.37
     servidor
    0.36
     alti
    0.36
     Courthouse
    0.36
    ༢
    0.36
     INSURANCE
    0.35
    POSITIVE LOGITS
    umet
    0.41
     coloration
    0.40
     bip
    0.38
    经典的
    0.38
     predominate
    0.37
     dipole
    0.37
     dyads
    0.37
    KeepOriginal
    0.37
     malleable
    0.37
    Kol
    0.35
    Activations Density 0.053%

    No Known Activations