© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40819
    Prev
    Next
    INDEX
    Explanations

    freedom and liberty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    c
    0.68
    p
    0.65
    on
    0.65
    기
    0.64
    𝙥
    0.63
    צ
    0.63
    G
    0.62
     количе
    0.60
    Army
    0.59
    l
    0.59
    POSITIVE LOGITS
    自由
    1.45
     freedom
    1.41
     free
    1.35
     자유
    1.35
     libertà
    1.29
     liberté
    1.27
     свобо
    1.27
     freed
    1.23
     libertad
    1.23
     liberdade
    1.21
    Activations Density 0.035%

    No Known Activations