© 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. 156850
    Prev
    Next
    INDEX
    Explanations

    sponsoring the

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

    insured, battery, owners

    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
     глаза
    0.46
    㓞
    0.45
     కృషి
    0.45
    以及
    0.44
     الموضوع
    0.43
    wt
    0.43
    ке
    0.42
    ৩
    0.42
    搅拌
    0.42
     жест
    0.42
    POSITIVE LOGITS
     salespeople
    0.52
     sativa
    0.52
     wallpapers
    0.51
     ebooks
    0.50
     posibles
    0.50
     srebr
    0.49
     europa
    0.49
     messengers
    0.48
     chatbots
    0.48
     backpacks
    0.48
    Activations Density 0.000%

    No Known Activations