© 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. 179846
    Prev
    Next
    INDEX
    Explanations

    gas, bench, Jesus, single

    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
    ెర
    0.52
    নকে
    0.49
    ídu
    0.48
    庸
    0.47
     Tud
    0.46
     Wied
    0.46
    र्में
    0.46
     Larg
    0.46
     tiu
    0.46
    嶇
    0.46
    POSITIVE LOGITS
     बचा
    0.50
    Save
    0.49
     मशी
    0.46
     উপস্থিতি
    0.44
    downloads
    0.44
     đa
    0.43
    Pay
    0.43
    していた
    0.43
     etiqueta
    0.43
     Национальный
    0.43
    Activations Density 0.000%

    No Known Activations