© 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. 12169
    Prev
    Next
    INDEX
    Explanations

    whatever you need

    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
    eem
    1.90
    es
    1.78
    𝙜
    1.77
     eld
    1.68
    𝐩
    1.63
    unsplash
    1.60
     harbour
    1.58
    printStackTrace
    1.57
    𝐦
    1.57
    𝐇
    1.57
    POSITIVE LOGITS
    ọ
    1.95
    oretto
    1.92
     xếp
    1.90
     अंजाम
    1.88
    ٭
    1.87
     आखिर
    1.85
    双方
    1.81
     сообщи
    1.81
    ERY
    1.80
    ͯ
    1.77
    Activations Density 0.000%

    No Known Activations