© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57573
    Prev
    Next
    INDEX
    Explanations

    tariffs on goods

    np_acts-logits-general · gemini-2.5-flash-lite

    Evangelion, feature development, cell cycle arrest, travertine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     secara
    0.57
     Mandalorian
    0.51
     यानी
    0.49
    コロナ
    0.49
    )$.
    0.49
     povos
    0.48
     코로나
    0.48
     जनसंख्या
    0.48
     doesn
    0.46
     can
    0.46
    POSITIVE LOGITS
    ---------*/
    0.44
    CollectedField
    0.41
    acr
    0.41
    touchstart
    0.41
    mal
    0.40
    itaan
    0.40
    appui
    0.40
    ettel
    0.40
    량을
    0.39
     দলিল
    0.39
    Activations Density 0.000%

    No Known Activations