© 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. 112378
    Prev
    Next
    INDEX
    Explanations

    mineral processing, mining, or technology

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

    initial state or action

    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
     января
    0.62
    aron
    0.56
     січня
    0.52
    িন
    0.50
    glColor
    0.47
    anez
    0.47
     দ্র
    0.46
    ၤ
    0.46
    glVertex
    0.46
    än
    0.45
    POSITIVE LOGITS
     capacities
    0.52
     multiplex
    0.49
     hexagonal
    0.48
     cobertura
    0.46
     cursed
    0.46
     stabilise
    0.46
     neutralize
    0.46
     compensate
    0.45
     stably
    0.45
     defended
    0.45
    Activations Density 0.001%

    No Known Activations