© 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. 15153
    Prev
    Next
    INDEX
    Explanations

    answer

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

    providing answers

    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
     inquis
    0.43
     approximating
    0.42
     জিজ্ঞাস
    0.42
     inquisitive
    0.41
     equivalente
    0.41
     odpowiedzial
    0.41
    𝕄
    0.41
     якщо
    0.40
    抱着
    0.40
     drunkenness
    0.40
    POSITIVE LOGITS
     supplements
    0.46
     sublicense
    0.42
    에도
    0.41
     每
    0.41
     prefs
    0.39
     workshops
    0.38
     Metabol
    0.38
     Proc
    0.37
    fromParams
    0.37
    延
    0.36
    Activations Density 0.000%

    No Known Activations