© 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. 45094
    Prev
    Next
    INDEX
    Explanations

    patriarchal, oppression, suppressing

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

    ML and CI terms

    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
     habitat
    0.47
     -
    0.46
     \\
    0.45
    _
    0.44
     was
    0.44
     distance
    0.44
     اختر
    0.43
     ।
    0.42
     。
    0.42
     distances
    0.42
    POSITIVE LOGITS
     हराकर
    0.45
     उत्पीड़न
    0.45
     এইসব
    0.44
     patriarchal
    0.43
     वैदिक
    0.42
     মানুষকে
    0.41
    }^{+}+
    0.41
     misog
    0.41
     suppressing
    0.41
     repressive
    0.41
    Activations Density 0.000%

    No Known Activations