© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12215
    Prev
    Next
    INDEX
    Explanations

    societal norms and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    す楽
    3.00
    িণ
    2.95
    ্ক
    2.83
     obdob
    2.81
    ﺔ
    2.80
     mekanisme
    2.77
    }\{\
    2.77
    ವಾಗಿ
    2.75
    া
    2.75
     prawidł
    2.74
    POSITIVE LOGITS
    yy
    2.64
    Ben
    2.49
    ュー
    2.47
    With
    2.40
    WITH
    2.37
    journey
    2.31
     discharge
    2.30
    ยว
    2.26
     Ben
    2.21
    entrée
    2.20
    Activations Density 0.015%

    No Known Activations