© 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. 49243
    Prev
    Next
    INDEX
    Explanations

    contractual and financial terms

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

    democratic governance and innovation

    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
    द
    0.49
    Ukraine
    0.46
    Manufact
    0.44
    umbre
    0.44
    l
    0.43
     galvanized
    0.42
    I
    0.41
    mist
    0.40
    ignored
    0.40
     totalled
    0.40
    POSITIVE LOGITS
     Prayers
    0.48
     Proteins
    0.47
     Breeding
    0.47
     `<`,
    0.46
    дится
    0.46
     Critical
    0.46
    的说
    0.46
    靣
    0.45
     Sought
    0.45
     Propagation
    0.45
    Activations Density 0.000%

    No Known Activations