© 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. 88157
    Prev
    Next
    INDEX
    Explanations

    sequences ending with "again later" or "very different"

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

    one two

    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
     усіх
    0.50
    preceq
    0.48
     અને
    0.47
     və
    0.47
     []);
    0.47
     ਅਤੇ
    0.46
    <unused93>
    0.45
    🍡
    0.45
     समस्त
    0.45
     ATTORNEY
    0.45
    POSITIVE LOGITS
    bow
    0.48
     trunks
    0.45
     bolts
    0.45
    ありません
    0.44
    威尔
    0.44
    シ
    0.43
    述
    0.42
    惻
    0.42
    ارت
    0.41
    boor
    0.41
    Activations Density 0.001%

    No Known Activations