© 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. 112152
    Prev
    Next
    INDEX
    Explanations

    born, equilibrium, employees, travel, rate

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

    expect or advise on sequences

    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
    驒
    0.50
    枷
    0.48
    िरी
    0.48
    崠
    0.47
    იტ
    0.47
     потрібно
    0.46
    限制
    0.46
    咵
    0.46
    AntiForgery
    0.46
    睃
    0.46
    POSITIVE LOGITS
    at
    0.49
    Ln
    0.44
     hemisph
    0.44
     geboren
    0.44
    bf
    0.43
     Universidad
    0.43
     avec
    0.42
    stdio
    0.42
    }");
    0.41
     endowed
    0.41
    Activations Density 0.000%

    No Known Activations