© 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. 133334
    Prev
    Next
    INDEX
    Explanations

    Access to stages or alerts

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

    medical notes and lists

    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
    OF
    0.54
     čak
    0.49
    يّ
    0.49
    COUNTS
    0.48
     kanya
    0.46
    KAN
    0.46
    ᱖
    0.46
     kinder
    0.46
    dienst
    0.46
     veritable
    0.46
    POSITIVE LOGITS
     Stages
    0.44
     Acces
    0.44
    ال
    0.43
     Fragments
    0.43
    </h2>
    0.43
     Access
    0.43
    హ
    0.42
     acess
    0.42
    每个人
    0.42
     alerts
    0.41
    Activations Density 0.000%

    No Known Activations