© 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. 104214
    Prev
    Next
    INDEX
    Explanations

    administration, federal, schemes

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

    storing and suggesting actions

    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
    0.64
     lhs
    0.57
     bx
    0.55
    .
    0.53
     rc
    0.52
     prev
    0.52
     dp
    0.52
    。
    0.52
     Illinois
    0.51
     kwenye
    0.51
    POSITIVE LOGITS
    Telecom
    0.54
     архіви
    0.51
     регла
    0.51
    Administrative
    0.50
    Hospital
    0.50
    Webhook
    0.50
    运营
    0.49
    зяржа
    0.49
    assapi
    0.49
    Employees
    0.48
    Activations Density 0.000%

    No Known Activations