© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10497
    Prev
    Next
    INDEX
    Explanations

    HTML tags button and p

    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
    eeee
    2.68
    ordinaire
    2.33
    eee
    2.28
    eaa
    2.25
    षण
    2.18
    ffekt
    2.17
    특
    2.17
    g
    2.13
    gger
    2.10
    cccc
    2.07
    POSITIVE LOGITS
    ﺔ
    2.91
    abhas
    2.39
    ﻲ
    2.30
    Fragments
    2.30
    鸯
    2.24
    াসেব
    2.20
    orus
    2.18
    hão
    2.14
    стей
    2.14
    姆斯
    2.13
    Activations Density 0.026%

    No Known Activations