© 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. 41515
    Prev
    Next
    INDEX
    Explanations

    consumer goods and measurements

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

    requires

    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
     désir
    0.52
    ពួក
    0.52
     பின்ன
    0.49
    忉
    0.49
     व्यवस्था
    0.49
    តែ
    0.48
     jelen
    0.47
     tạm
    0.47
     scén
    0.46
     பகை
    0.46
    POSITIVE LOGITS
     Consume
    0.46
     energy
    0.45
     coated
    0.44
    km
    0.43
    ΗΣ
    0.43
     Consumer
    0.42
     k
    0.42
     to
    0.42
     consumer
    0.41
    cm
    0.41
    Activations Density 0.000%

    No Known Activations