© 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. 3835
    Prev
    Next
    INDEX
    Explanations

    questions

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

    questions starting with what or question

    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
     Oficina
    0.41
     heut
    0.38
     Circuit
    0.38
     Cott
    0.38
     Ithaca
    0.38
    next
    0.37
    n
    0.37
     introduces
    0.37
     palladium
    0.37
     Celle
    0.37
    POSITIVE LOGITS
     QUESTION
    0.66
     spør
    0.63
    सवाल
    0.62
     pregunta
    0.61
    QUESTION
    0.61
     السؤال
    0.60
    Question
    0.59
     otáz
    0.59
     問
    0.59
     QUESTIONS
    0.58
    Activations Density 0.001%

    No Known Activations