© 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. 80867
    Prev
    Next
    INDEX
    Explanations

    setting study

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

    foundational concepts and learning

    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
    긍
    0.47
     duit
    0.44
    और
    0.44
     છીએ
    0.42
     puns
    0.42
    ছিলাম
    0.41
    紋
    0.41
     grooves
    0.41
     subcut
    0.41
    ჩ
    0.41
    POSITIVE LOGITS
    ješt
    0.48
     Tests
    0.48
     Testing
    0.46
    Tests
    0.45
     Conceptual
    0.45
    Conceptual
    0.45
     Preparing
    0.44
     Simplifying
    0.44
     Entwicklung
    0.44
     Analysis
    0.43
    Activations Density 0.000%

    No Known Activations