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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29196
    Prev
    Next
    INDEX
    Explanations

    socially liberal views

    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
     coeur
    0.47
     Giveen
    0.46
     coraz
    0.46
     endereço
    0.45
     نيك
    0.44
    និយ
    0.43
    圏
    0.43
     родился
    0.43
    🏟
    0.43
    拠
    0.42
    POSITIVE LOGITS
     tricky
    0.44
    aphr
    0.43
    ilu
    0.41
     stinging
    0.41
    afu
    0.41
     elution
    0.39
    assan
    0.39
     touch
    0.39
    putation
    0.39
    mixture
    0.39
    Activations Density 0.005%

    No Known Activations