© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15465
    Prev
    Next
    INDEX
    Explanations

    shower

    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_13_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
    ிறது
    2.35
     महामंत्री
    1.96
    ிறார்கள்
    1.93
    Account
    1.90
    𝙢
    1.85
    𝙠
    1.85
    傢
    1.81
    ्‍य
    1.78
    ભગ
    1.75
    ल्याण
    1.74
    POSITIVE LOGITS
    <bos>
    3.00
    ্ড
    2.88
    ﻙ
    2.34
    er
    2.32
    ៉ុ
    2.32
    erar
    2.31
    此之外
    2.27
    یدر
    2.26
     वीं
    2.24
    ៊
    2.18
    Activations Density 0.014%

    No Known Activations