© 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. 57929
    Prev
    Next
    INDEX
    Explanations

    spray foam, monitor blood, roasting food

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

    subject-verb agreement

    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
    u
    0.59
    ga
    0.50
    millis
    0.50
    rand
    0.49
    ms
    0.49
    dub
    0.49
    transformation
    0.48
     গাঁ
    0.47
    π
    0.47
    me
    0.46
    POSITIVE LOGITS
     horaires
    0.49
     larg
    0.48
     purify
    0.47
     nourish
    0.47
     prid
    0.47
     Casi
    0.47
     organize
    0.46
     palestra
    0.46
     AcOEt
    0.46
     cantidades
    0.46
    Activations Density 0.000%

    No Known Activations