© 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. 3735
    Prev
    Next
    INDEX
    Explanations

    ideologies and beliefs

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

    isms and ideologies

    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
    data
    0.58
    k
    0.57
    这个
    0.55
    s
    0.55
    kable
    0.54
    size
    0.53
    da
    0.51
     माइट
    0.51
    6
    0.51
    season
    0.50
    POSITIVE LOGITS
     liberalism
    0.71
     ideology
    0.68
    主义
    0.68
     individualism
    0.67
     pensamiento
    0.63
     extremism
    0.63
     feminism
    0.62
    istische
    0.61
    主義
    0.60
     creencias
    0.60
    Activations Density 0.135%

    No Known Activations