© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4100
    Prev
    Next
    INDEX
    Explanations

    This followed by explanation verb

    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
    Negative Logits
     …
    2.68
    isatie
    2.34
    re
    2.32
     ….
    2.30
    ically
    2.26
    ionic
    2.22
    TAINS
    2.20
    uclear
    2.18
     remo
    2.17
    ALLY
    2.17
    POSITIVE LOGITS
    arı
    2.71
    ScheduledAction
    2.65
    
    2.62
    佼
    2.53
     имущества
    2.53
    guardo
    2.53
    诵
    2.51
    ാ
    2.49
    脱
    2.48
    MakeRange
    2.47
    Activations Density 0.042%

    No Known Activations