© 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. 79247
    Prev
    Next
    INDEX
    Explanations

    word parts and context

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

    wanna chat

    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
    эй
    0.48
    триму
    0.48
     ovu
    0.46
     فور
    0.45
    它可以
    0.45
     candidato
    0.44
    ынша
    0.44
     첫
    0.42
    верка
    0.42
     construed
    0.42
    POSITIVE LOGITS
     étudier
    0.50
    ম
    0.49
    further
    0.46
     вста
    0.46
    avad
    0.46
     Matrices
    0.46
    ⊹
    0.45
    Gn
    0.44
    ME
    0.44
    ème
    0.44
    Activations Density 0.001%

    No Known Activations