© 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. 2353
    Prev
    Next
    INDEX
    Explanations

    layering sounds and elements

    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
    MaxWidth
    1.43
    CHREIB
    1.41
     basé
    1.34
     atau
    1.33
     partant
    1.32
    ወቅ
    1.28
    별
    1.28
     দিনের
    1.28
    を指定
    1.27
    POST
    1.25
    POSITIVE LOGITS
    shima
    1.90
    嗬
    1.78
     リュ
    1.67
     られ
    1.55
     अकादमी
    1.54
     ブルー
    1.54
     bronze
    1.51
    enciaga
    1.50
    oyloxy
    1.49
    ônia
    1.48
    Activations Density 0.090%

    No Known Activations