© 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. 127528
    Prev
    Next
    INDEX
    Explanations

    professors, manufacturers, women

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

    adding or discovering something

    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
    4
    0.45
    6
    0.44
    7
    0.44
    ']);
    0.43
    8
    0.43
    X
    0.43
     Episodes
    0.43
    5
    0.42
    0
    0.42
     Memory
    0.42
    POSITIVE LOGITS
    女士
    0.52
     fabricante
    0.50
    硕士
    0.47
     profesor
    0.47
     प्रोफेसर
    0.46
     امرأة
    0.45
    ጴ
    0.45
    штейн
    0.44
     fabricant
    0.43
    購入
    0.43
    Activations Density 0.000%

    No Known Activations