© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14565
    Prev
    Next
    INDEX
    Explanations

    introduction followed by punctuation

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

    introduction

    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_16k_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
    엑
    0.47
    К
    0.45
    nat
    0.45
    ال
    0.44
    s
    0.43
    urine
    0.42
    下拉
    0.41
    circ
    0.40
    在
    0.40
    第
    0.40
    POSITIVE LOGITS
     Harrier
    0.50
    erden
    0.43
     obligaciones
    0.42
     HAR
    0.41
     Caledonia
    0.41
    Storia
    0.40
    ल्स
    0.40
     പ്രതീക്ഷ
    0.39
     arrivare
    0.39
     والب
    0.39
    Activations Density 0.000%

    No Known Activations