© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13846
    Prev
    Next
    INDEX
    Explanations

    Anyone else

    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
    𝐫
    2.83
    œil
    2.77
    𝐝
    2.70
    𝐡
    2.69
    Datetime
    2.67
    𝐭
    2.66
    ﻤ
    2.62
    Jwt
    2.60
    𝐥
    2.60
    ग्विजय
    2.54
    POSITIVE LOGITS
    ي
    3.03
    fully
    2.58
    ுள்ளார்
    2.40
    根
    2.38
    ιβ
    2.30
    j
    2.28
    ுள்ள
    2.22
    ের
    2.21
    isit
    2.21
    is
    2.14
    Activations Density 0.005%

    No Known Activations