© 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. 152510
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating duration or method

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

    smell, tongue, and spending time

    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
     career
    0.54
     Career
    0.52
    安
    0.50
    Career
    0.47
    目前
    0.46
    \|
    0.45
     currently
    0.44
     benefitted
    0.44
    品
    0.44
    career
    0.43
    POSITIVE LOGITS
     bahawa
    0.57
     oznacza
    0.51
     plutôt
    0.50
     segala
    0.50
     banane
    0.50
     apapun
    0.50
     restric
    0.50
    anje
    0.49
     inclin
    0.49
     različ
    0.48
    Activations Density 0.000%

    No Known Activations