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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40819
    Prev
    Next
    INDEX
    Explanations

    free or freedom

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

    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-pt/resid_post/layer_31_width_262k_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
    c
    0.70
    きちんと
    0.62
    G
    0.62
    צ
    0.61
    })$
    0.60
    l
    0.60
    기
    0.59
     않
    0.59
    𝙥
    0.59
    绚
    0.58
    POSITIVE LOGITS
     free
    1.51
    自由
    1.50
     freedom
    1.45
     자유
    1.39
     freed
    1.38
     свобо
    1.36
     liberté
    1.34
     свобод
    1.30
     libertà
    1.29
     Freedom
    1.27
    Activations Density 0.068%

    No Known Activations