© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2190
    Prev
    Next
    INDEX
    Explanations

    common identifiers

    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
     за
    1.25
     indel
    1.16
    ال
    1.11
    unched
    1.08
     произ
    1.08
     и
    1.07
     nad
    1.07
     на
    1.06
    უნქ
    1.05
     preconceived
    1.05
    POSITIVE LOGITS
    खास्त
    1.47
    ếm
    1.30
     ramai
    1.27
    ত্ত্ব
    1.24
    ਗੀ
    1.23
    绎
    1.17
    üğü
    1.16
    먀
    1.15
    ਾਨ
    1.15
     vận
    1.15
    Activations Density 0.146%

    No Known Activations