© 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. 55072
    Prev
    Next
    INDEX
    Explanations

    IBM global operations

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

    global corporations and enterprise

    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
    螓
    0.48
     Decay
    0.47
     convexes
    0.45
     తి
    0.44
    bandSize
    0.43
     Interchange
    0.43
     Reaper
    0.43
    霏
    0.43
     Bar
    0.43
    ৃতির
    0.43
    POSITIVE LOGITS
    global
    0.82
     global
    0.76
     глоба
    0.72
    全球
    0.71
    IBM
    0.70
    在全球
    0.67
     वैश्विक
    0.64
     globales
    0.64
    lobal
    0.63
    ibm
    0.63
    Activations Density 0.160%

    No Known Activations