© 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. 209375
    Prev
    Next
    INDEX
    Explanations

    rules provided for

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

    sequential tasks and models

    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
    ק
    0.43
    ፖ
    0.42
    েম
    0.42
    湊
    0.42
    満足
    0.42
    涔
    0.41
    ंपल
    0.41
    ifford
    0.40
    Қ
    0.40
    噎
    0.40
    POSITIVE LOGITS
     домаћинства
    0.52
     вс
    0.47
     caching
    0.46
     запа
    0.44
    DCs
    0.44
     রানী
    0.43
     পুনরায়
    0.43
     বলেছিলেন
    0.43
     rundown
    0.42
     CPUs
    0.42
    Activations Density 0.001%

    No Known Activations