© 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. 30391
    Prev
    Next
    INDEX
    Explanations

    following reconciliation

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

    tomato paste and stream events

    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
    ¹
    0.43
    šia
    0.43
    ní
    0.42
     positiv
    0.41
     hoffe
    0.41
     nejen
    0.41
    苗
    0.40
    結論
    0.40
     Poli
    0.40
    すなわち
    0.39
    POSITIVE LOGITS
    ادیه
    0.51
     گذشته
    0.48
    াপনের
    0.46
     HMRC
    0.45
    বাজারে
    0.44
    личество
    0.44
    لبوم
    0.44
     আরেকটি
    0.43
    昨年
    0.43
    گرد
    0.42
    Activations Density 0.000%

    No Known Activations