© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6407
    Prev
    Next
    INDEX
    Explanations

    renewable energy sources

    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_15_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
    чете
    1.25
    эння
    1.25
     pessoa
    1.25
     някои
    1.22
     pessoas
    1.21
    一眼
    1.18
    瘾
    1.18
     governo
    1.15
     galera
    1.14
     pengend
    1.13
    POSITIVE LOGITS
    hout
    1.64
    iary
    1.60
    ivables
    1.54
    ין
    1.51
    raiser
    1.49
    rified
    1.43
    RequestBuilder
    1.42
     lending
    1.41
    啬
    1.38
    volence
    1.37
    Activations Density 0.035%

    No Known Activations