© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87823
    Prev
    Next
    INDEX
    Explanations

    information, process, object, data

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

    avoiding overfitting and deploying

    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
    єм
    0.55
    คัญ
    0.52
    orient
    0.50
    логи
    0.49
    asign
    0.49
    ovember
    0.47
     бясплатна
    0.46
    윰
    0.46
    향
    0.45
    wią
    0.45
    POSITIVE LOGITS
     backups
    0.50
     militias
    0.47
     minus
    0.45
     transgenic
    0.45
     faults
    0.45
     planes
    0.44
     shelling
    0.44
     balloon
    0.44
     formulas
    0.44
     safeguards
    0.43
    Activations Density 0.002%

    No Known Activations