© 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. 191571
    Prev
    Next
    INDEX
    Explanations

    specific words like upon, Linux, tycoon

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

    American history and politics

    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
    ب
    0.59
    б
    0.54
    ஒரு
    0.54
    குடும்ப
    0.53
    Д
    0.52
    ט
    0.51
    అ
    0.50
    囹
    0.50
    IRY
    0.49
    مام
    0.48
    POSITIVE LOGITS
    phonic
    0.45
    hire
    0.45
    civil
    0.44
    cyclic
    0.43
     Bonifacio
    0.43
    erving
    0.43
    acetate
    0.42
    ermark
    0.42
    jim
    0.41
     taint
    0.41
    Activations Density 0.001%

    No Known Activations