© 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. 153381
    Prev
    Next
    INDEX
    Explanations

    cost, medical, help, readers, biscuits

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

    keywords:

    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
    onian
    0.55
    the
    0.49
    G
    0.48
    ages
    0.48
    hesion
    0.48
    ure
    0.48
    iams
    0.48
    efe
    0.47
    orsement
    0.47
    codes
    0.47
    POSITIVE LOGITS
     keyPressed
    0.51
     derzeit
    0.47
     factores
    0.47
    燼
    0.47
     руководи
    0.46
    TRANSPORT
    0.46
     infringing
    0.45
    mce
    0.44
    েম
    0.44
     সঙ্ক
    0.44
    Activations Density 0.000%

    No Known Activations