© 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. 2007
    Prev
    Next
    INDEX
    Explanations

    VPN and squats

    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
    ei
    3.58
    e
    3.35
    る
    3.28
    ت
    3.22
    ing
    3.18
    i
    3.15
    ed
    3.11
    るのは
    3.03
    as
    2.98
    ेक्ट
    2.97
    POSITIVE LOGITS
    𝐫
    2.99
    𝐭
    2.93
    𝐡
    2.92
    +](=
    2.88
    𝐨
    2.82
    櫚
    2.78
    𝐧
    2.75
    ﻡ
    2.74
    𝐦
    2.73
    вает
    2.72
    Activations Density 0.000%

    No Known Activations