© 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. 137074
    Prev
    Next
    INDEX
    Explanations

    years and dates

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

    meaning the yerida

    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
     изображение
    0.44
    旗
    0.44
     تصویر
    0.43
    бан
    0.43
    <0xE3>
    0.42
     в
    0.42
     изображения
    0.41
    写真を
    0.41
    Pics
    0.41
     фотографи
    0.40
    POSITIVE LOGITS
    ఞ
    0.51
     කිය
    0.45
     WI
    0.43
    ర్జ
    0.41
     larg
    0.40
     headache
    0.40
     dosage
    0.40
     nilpotent
    0.40
     evaluator
    0.40
     divide
    0.40
    Activations Density 0.001%

    No Known Activations