© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    get to or for

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

    get started

    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
     Gave
    0.36
     বিপক্ষে
    0.34
    gave
    0.31
     Being
    0.30
     gegeben
    0.30
    {~
    0.29
    ալ
    0.28
    を受けて
    0.28
    endsWith
    0.28
    羮
    0.28
    POSITIVE LOGITS
     rid
    1.27
     acquainted
    1.05
     involved
    0.84
     started
    0.82
     accustomed
    0.81
     excited
    0.75
     into
    0.75
    rid
    0.73
     caught
    0.73
     stuck
    0.73
    Activations Density 0.279%

    No Known Activations