© 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. 3949
    Prev
    Next
    INDEX
    Explanations

    concepts on a spectrum

    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
    ፈላጊ
    1.43
     ciò
    1.40
    𝗥
    1.39
    য়ো
    1.38
     cuero
    1.38
     inoxidable
    1.37
     thisTrial
    1.37
    𝗰
    1.37
    िफिशियल
    1.37
    ंपरा
    1.36
    POSITIVE LOGITS
    ing
    1.29
    s
    1.20
    na
    1.18
    teenth
    1.18
    sa
    1.17
    amal
    1.17
    ne
    1.17
    ske
    1.17
    ments
    1.16
    ielen
    1.13
    Activations Density 0.001%

    No Known Activations