© 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. 8131
    Prev
    Next
    INDEX
    Explanations

    callingcallingcallcallcallingcallcallcallcallcall

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

    crisis text line 741741

    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
    рованных
    0.38
     Dasar
    0.38
    믹
    0.38
    经典的
    0.37
    各个
    0.37
     Wordpress
    0.37
     Cig
    0.36
    rufen
    0.35
    傅
    0.35
    rograman
    0.35
    POSITIVE LOGITS
    edale
    0.44
    anooga
    0.42
    崙
    0.39
     hurts
    0.38
    洒落
    0.38
    าราง
    0.38
    ربع
    0.38
    स्पीड
    0.37
    ১২
    0.37
    ⑮
    0.36
    Activations Density 0.027%

    No Known Activations