© 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. 39051
    Prev
    Next
    INDEX
    Explanations

    phrases like to work, at the, for $

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

    data storytelling for business impact

    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
    他
    0.48
     приложения
    0.46
     அவர்
    0.45
    Superview
    0.45
     కనిప
    0.44
    医院
    0.44
     అభిమా
    0.44
     হাসপাতাল
    0.44
    నుంది
    0.44
    颀
    0.44
    POSITIVE LOGITS
     sce
    0.56
     shield
    0.54
    i
    0.51
     nutrients
    0.51
     seller
    0.50
    a
    0.50
     walls
    0.50
     pout
    0.50
     wires
    0.49
     sin
    0.48
    Activations Density 0.001%

    No Known Activations