© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12989
    Prev
    Next
    INDEX
    Explanations

    organizations and structured data

    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_13_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
     rumus
    1.51
     metoda
    1.40
    rouw
    1.35
     mulher
    1.34
     বৈঠ
    1.34
    anceled
    1.31
     rynku
    1.31
    粤
    1.31
    त्तीस
    1.30
    when
    1.30
    POSITIVE LOGITS
    nesses
    1.41
     ness
    1.41
     legitimately
    1.36
     sett
    1.30
     teething
    1.30
     Corridor
    1.29
    ":
    1.26
    <unused2157>
    1.25
     extraordin
    1.23
     Elsewhere
    1.23
    Activations Density 0.000%

    No Known Activations