© 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. 11082
    Prev
    Next
    INDEX
    Explanations

    2 to

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

    interest on savings

    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
    ј
    0.53
    その
    0.52
    ля
    0.50
    ところ
    0.49
    я
    0.48
    Nev
    0.47
    Howard
    0.47
    亮
    0.46
    買
    0.46
    藍
    0.46
    POSITIVE LOGITS
     problema
    0.52
     teori
    0.51
     merasa
    0.50
     envis
    0.50
     erwarten
    0.48
     paham
    0.48
     centuries
    0.47
     shalt
    0.47
     relieved
    0.46
     系统
    0.46
    Activations Density 0.000%

    No Known Activations