© 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. 2899
    Prev
    Next
    INDEX
    Explanations

    to be or to have

    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
    makeConstraints
    2.01
     hacked
    1.93
    ITIONAL
    1.93
     ‘
    1.89
     hydrolyzed
    1.81
     (‘
    1.80
     wouldn
    1.77
     firstly
    1.74
    pox
    1.73
    ayer
    1.71
    POSITIVE LOGITS
    𝐬
    3.14
    𝐫
    2.90
    𝐥
    2.78
    𝐤
    2.75
    𝐡
    2.73
    rifuge
    2.67
    𝐣
    2.63
    𝐠
    2.56
    #"
    2.46
    ﻳ
    2.44
    Activations Density 0.115%

    No Known Activations