© 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. 21654
    Prev
    Next
    INDEX
    Explanations

    and then

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

    Use Case: serialization

    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
    ιδ
    0.47
    Ag
    0.43
    ྒྱ
    0.41
    د
    0.41
    Ny
    0.39
    ง
    0.39
    渔
    0.38
    Syl
    0.38
    ومی
    0.38
    𝑤
    0.38
    POSITIVE LOGITS
     came
    0.47
     preced
    0.45
     そして
    0.43
     microphone
    0.43
     member
    0.42
     Conte
    0.42
     Cote
    0.42
     previos
    0.42
     Second
    0.41
     newcomer
    0.41
    Activations Density 0.000%

    No Known Activations