© 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. 3833
    Prev
    Next
    INDEX
    Explanations

    job application documents

    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
     Ngf
    2.46
     Eminent
    2.38
    ో
    2.33
    Computed
    2.30
    MACl
    2.29
    ])).
    2.28
    stackpath
    2.26
    "]).
    2.23
    anlage
    2.21
     afterDir
    2.20
    POSITIVE LOGITS
     canad
    2.36
    𝗱
    2.29
     Winnipeg
    2.12
    Ontario
    2.11
     Vancouver
    2.00
     qué
    1.97
     cuy
    1.92
     विपरीत
    1.90
     Ontario
    1.88
    ᖁ
    1.88
    Activations Density 0.401%

    No Known Activations