© 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. 87350
    Prev
    Next
    INDEX
    Explanations

    overall length

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

    was thinking about

    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
     प्रयोग
    0.45
    ference
    0.44
     serving
    0.44
     mø
    0.43
     referência
    0.43
     oligodend
    0.43
     denotes
    0.42
    ：
    0.42
     finishes
    0.42
    而不是
    0.42
    POSITIVE LOGITS
    פים
    0.47
    ος
    0.46
    䖝
    0.45
    ofi
    0.45
    ()">
    0.44
    ונה
    0.44
    ifal
    0.44
    леге
    0.44
    าส
    0.44
    온
    0.43
    Activations Density 0.001%

    No Known Activations