© 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. 13048
    Prev
    Next
    INDEX
    Explanations

    multilingual concepts

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

    pondering complex questions

    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
     diffraction
    0.57
     sculpture
    0.52
     best
    0.49
     him
    0.46
     chalc
    0.46
     sculptures
    0.45
     radioactivity
    0.45
    技
    0.45
     his
    0.44
     unusually
    0.44
    POSITIVE LOGITS
     Millennials
    0.65
     kiddos
    0.59
    잖아요
    0.57
     equates
    0.57
     sottoline
    0.56
    ogliamo
    0.55
     oczywiście
    0.55
     ovviamente
    0.54
    हमें
    0.54
     iniziamo
    0.53
    Activations Density 0.107%

    No Known Activations