© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    relative to or followed by specific words

    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
    ez
    1.81
    П
    1.77
    Patch
    1.68
    क्राम
    1.68
    Sticky
    1.66
     PATCH
    1.65
    ᱥ
    1.64
    委员
    1.62
    ー
    1.60
     permut
    1.59
    POSITIVE LOGITS
    inding
    1.51
     desirous
    1.51
     Anspruch
    1.51
    âme
    1.45
     producing
    1.44
    玑
    1.44
     raising
    1.43
     behe
    1.42
    ocular
    1.40
     Producing
    1.36
    Activations Density 0.000%

    No Known Activations