© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47369
    Prev
    Next
    INDEX
    Explanations

    oppression, horrors, communists, political issues

    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
     महत्व
    0.45
     documenting
    0.42
    𝕖
    0.42
    違い
    0.42
    功率
    0.42
    季节
    0.41
     achieved
    0.41
     Teaching
    0.41
    🧁
    0.41
     पेपर
    0.40
    POSITIVE LOGITS
     oppression
    0.51
    judice
    0.46
     amenaza
    0.46
     horrors
    0.43
     এদেশে
    0.42
     communists
    0.42
    نې
    0.41
     ഭൂ
    0.41
     communist
    0.40
     oppressive
    0.40
    Activations Density 0.001%

    No Known Activations