© 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. 14885
    Prev
    Next
    INDEX
    Explanations

    numbers in codes or product ids

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

    numbers and non-latin characters

    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
    5
    0.59
    4
    0.59
    +
    0.58
    9
    0.56
    3
    0.54
    -
    0.54
    ↵
    0.51
    0
    0.51
    2
    0.51
    7
    0.50
    POSITIVE LOGITS
    𒋙
    0.39
    ANGMAR
    0.36
     кожного
    0.35
     banheiro
    0.34
    瘧
    0.34
    DanhMucSP
    0.34
    वारीत
    0.33
    窕
    0.33
    akkhati
    0.32
     ওষুধ
    0.32
    Activations Density 0.112%

    No Known Activations