© 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. 1676
    Prev
    Next
    INDEX
    Explanations

    common conditions and requirements

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

    confidential

    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
     són
    0.57
     Trebuie
    0.53
    Então
    0.52
    🏧
    0.52
    🚵
    0.51
     tão
    0.51
     levar
    0.49
    🍢
    0.49
     váy
    0.49
    🚞
    0.48
    POSITIVE LOGITS
     ampere
    1.52
     adenine
    1.47
     aforementioned
    1.16
     einige
    1.15
     wichtig
    1.14
     einigen
    1.14
     unmittel
    1.11
     welche
    1.10
     jeder
    1.09
     gemeinsamen
    1.09
    Activations Density 0.037%

    No Known Activations