© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9752
    Prev
    Next
    INDEX
    Explanations

    feminist viewpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
     keeping
    0.85
    re
    0.78
    }
    0.77
    he
    0.76
    '
    0.75
    }=$
    0.73
     H
    0.73
    {
    0.72
     K
    0.71
    -
    0.69
    POSITIVE LOGITS
    сным
    1.09
    сное
    1.03
     мастеров
    1.01
     может
    0.99
    вайтесь
    0.97
     органы
    0.96
    庤
    0.96
     территория
    0.95
     владель
    0.95
     связана
    0.94
    Activations Density 0.000%

    No Known Activations