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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2507
    Prev
    Next
    INDEX
    Explanations

    German "sch" followed by specific suffixes

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

    Spanish word beginnings

    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
     және
    0.27
    總
    0.26
    এই
    0.26
    عند
    0.26
    അ
    0.26
    десят
    0.25
     cria
    0.25
     καθώς
    0.24
     dessa
    0.24
    劶
    0.24
    POSITIVE LOGITS
    amping
    0.22
    up
    0.22
    ust
    0.21
    ump
    0.21
    rote
    0.21
    rp
    0.21
    ulat
    0.21
    ask
    0.21
    amp
    0.20
    r
    0.20
    Activations Density 0.049%

    No Known Activations