© 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. 88310
    Prev
    Next
    INDEX
    Explanations

    sector investment

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

    questions and definitions

    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
    粖
    0.50
     சுத்த
    0.49
     lelaki
    0.48
    舒適
    0.48
     bersih
    0.47
     serupa
    0.47
     logam
    0.47
     sahaja
    0.46
     وسی
    0.46
     сър
    0.46
    POSITIVE LOGITS
    n
    0.51
     አንዳንድ
    0.46
    Exception
    0.46
    inal
    0.45
     Return
    0.41
     Objection
    0.40
     unexpected
    0.40
    বেলা
    0.40
     azonban
    0.40
    unexpected
    0.40
    Activations Density 0.002%

    No Known Activations