© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8770
    Prev
    Next
    INDEX
    Explanations

    Quartär, Univers, Paläolithikum

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

    german umlauts and places

    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_53_width_65k_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
    CCION
    0.46
    叽
    0.46
     લગાવ
    0.44
    ́
    0.43
     pecado
    0.42
    시오
    0.42
     ܀
    0.42
     cifras
    0.42
     truss
    0.41
    рија
    0.41
    POSITIVE LOGITS
    ä
    1.62
    ö
    1.58
    äl
    1.45
    Ä
    1.45
    än
    1.42
    ät
    1.39
    är
    1.38
    lä
    1.38
     Ä
    1.38
    Ö
    1.37
    Activations Density 0.034%

    No Known Activations