© 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. 150710
    Prev
    Next
    INDEX
    Explanations

    enabling or disabling functionality

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

    child safety

    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
     Иванов
    0.42
    frag
    0.41
    货
    0.41
    มิ
    0.40
     부정
    0.40
     사라
    0.40
    LTE
    0.39
     frag
    0.38
     ผ
    0.38
    口碑
    0.38
    POSITIVE LOGITS
     utiliza
    0.49
    gio
    0.47
     Uses
    0.46
    たす
    0.45
     utilización
    0.45
     বিশেষজ্ঞ
    0.44
     criteri
    0.44
     uses
    0.43
     vyu
    0.43
     interventi
    0.43
    Activations Density 0.000%

    No Known Activations