© 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. 221189
    Prev
    Next
    INDEX
    Explanations

    assessments, appraisals, price, value

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

    Potentially, LEGOs, Santa

    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
     Обе
    0.58
     OMB
    0.52
     IUE
    0.51
    ᱗
    0.51
     Обще
    0.50
    聚集
    0.50
     Генера
    0.49
     Hogg
    0.48
     बीसीसीआई
    0.47
     Ат
    0.47
    POSITIVE LOGITS
     appraisals
    0.49
    พ
    0.49
    หาก
    0.48
    PRICE
    0.47
     saham
    0.47
     assessments
    0.46
    ・
    0.45
    EST
    0.45
     estatura
    0.45
    قیم
    0.44
    Activations Density 0.001%

    No Known Activations