© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7028
    Prev
    Next
    INDEX
    Explanations

    American museums and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    sede
    2.41
    fato
    2.38
    んで
    2.35
    jó
    2.35
    上位
    2.33
    上也
    2.32
    lü
    2.30
    餘
    2.29
    SPECT
    2.28
    킷
    2.27
    POSITIVE LOGITS
     Machinist
    1.18
    Cour
    1.16
    laştır
    1.15
     Serikat
    1.11
     Rein
    1.07
     început
    1.06
     Root
    1.04
    ppelin
    1.04
     Dream
    1.03
    sexual
    1.02
    Activations Density 0.043%

    No Known Activations