© 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. 12856
    Prev
    Next
    INDEX
    Explanations

    investment risk

    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
    ]::
    0.75
    ウェア
    0.72
    ิก
    0.72
     terg
    0.71
    謎
    0.71
     forcible
    0.71
    igrams
    0.70
    通販
    0.70
    گرام
    0.69
    菖
    0.69
    POSITIVE LOGITS
     dedi
    1.35
     beschrieben
    1.24
     gebo
    1.20
     empfohlen
    1.19
     Joz
    1.16
     nacht
    1.16
     JOSE
    1.15
     symphony
    1.15
     ajout
    1.15
     жа
    1.15
    Activations Density 0.093%

    No Known Activations