© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1328
    Prev
    Next
    INDEX
    Explanations

    that followed by verbs

    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
    estead
    1.46
    ayside
    1.34
    ogiri
    1.27
    ver
    1.25
    italization
    1.24
    凸
    1.24
    invest
    1.21
    ньо
    1.20
     heading
    1.19
     complete
    1.17
    POSITIVE LOGITS
    ﻐ
    2.23
     And
    2.18
     Và
    2.16
     וא
    2.09
     وت
    2.08
     অ্যান্ড
    2.08
     tę
    2.06
    端的
    2.02
     alcuna
    2.01
     وأ
    2.01
    Activations Density 0.033%

    No Known Activations