© 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. 16-GEMMASCOPE-2-RES-16K
    7. 485
    Prev
    Next
    INDEX
    Explanations

    calculation and time notation

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

    specific documentation and instructions

    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_16_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
    ة
    0.63
    ка
    0.59
    feeling
    0.56
     caráter
    0.54
    лни
    0.50
    шком
    0.50
    ško
    0.49
    voerd
    0.49
    ಈ
    0.49
     увеличи
    0.48
    POSITIVE LOGITS
    challeng
    0.63
     challenging
    0.52
     Challeng
    0.51
     du
    0.49
    orylation
    0.49
     classes
    0.48
     landfall
    0.48
     commissioning
    0.46
     manif
    0.46
     모든
    0.46
    Activations Density 0.000%

    No Known Activations