© 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. 4166
    Prev
    Next
    INDEX
    Explanations

    Get youra medievalthe presencethe solutionThe Quantum

    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
     opportune
    1.18
    ensia
    1.13
     mek
    1.13
    ...\...\...\...\
    1.11
    agma
    1.09
     misc
    1.08
    insley
    1.05
    鍘
    1.02
    уре
    1.02
    氏は
    1.01
    POSITIVE LOGITS
     Partizan
    1.81
     doped
    1.71
     Beton
    1.68
     superconduct
    1.65
     spiaggia
    1.65
    Minecraft
    1.63
     Praia
    1.63
     Toen
    1.63
     Gamer
    1.62
     Sauna
    1.62
    Activations Density 0.007%

    No Known Activations