© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11298
    Prev
    Next
    INDEX
    Explanations

    military or technical responsibilities

    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
    OutputStream
    3.00
    a
    2.67
    eae
    2.58
     ইপিআর
    2.58
    ه
    2.57
     охорони
    2.54
    یث
    2.52
    ポジ
    2.50
    рные
    2.50
    Cir
    2.49
    POSITIVE LOGITS
    ாக
    2.56
    শীল
    2.47
    챙
    2.24
    芏
    2.14
    trä
    2.10
    Ü
    2.06
    Us
    2.05
    ̷
    2.04
    कुंठ
    2.03
    ate
    1.99
    Activations Density 0.003%

    No Known Activations