© 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. 204254
    Prev
    Next
    INDEX
    Explanations

    government officials

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

    actions that can be done

    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
    ગા
    0.44
    gak
    0.44
     मिलीमीटर
    0.44
    過ご
    0.43
     gouttes
    0.43
    避
    0.43
    뵙
    0.43
    orgh
    0.42
    צ
    0.42
    aled
    0.42
    POSITIVE LOGITS
     nejsou
    0.51
     minister
    0.50
     PAN
    0.50
    minister
    0.48
     vary
    0.48
    institut
    0.47
    Aplic
    0.47
     ministry
    0.47
     niiden
    0.46
    DAM
    0.46
    Activations Density 0.000%

    No Known Activations