© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123675
    Prev
    Next
    INDEX
    Explanations

    financial condition

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

    patterns, influences, impacts, vulnerabilities

    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
    Negative Logits
    Brend
    0.53
    Harvey
    0.50
    Rachel
    0.49
    Sequ
    0.48
    Roy
    0.48
    he
    0.47
    Mark
    0.47
    领
    0.46
    amus
    0.46
    ként
    0.46
    POSITIVE LOGITS
     Ethiopia
    0.47
     Bosnia
    0.45
     পাট
    0.45
     Ад
    0.44
     hampered
    0.44
     extinguishers
    0.44
    ፑ
    0.44
     ij
    0.44
     折り
    0.44
    ICHIGAN
    0.43
    Activations Density 0.000%

    No Known Activations