© 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. 89609
    Prev
    Next
    INDEX
    Explanations

    Google USA

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

    linking words to outcomes

    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
    explique
    0.47
     redevelopment
    0.46
    ますが
    0.46
     ако
    0.45
    economic
    0.44
    𝙨
    0.43
     தண்ணீர்
    0.43
    
    0.43
    🖼
    0.42
     fleste
    0.42
    POSITIVE LOGITS
     Bytes
    0.48
     Revealed
    0.46
     omitted
    0.45
     fortaleza
    0.45
     Reporting
    0.44
     On
    0.43
     Publishing
    0.43
     informes
    0.43
     Zoe
    0.43
    OMe
    0.42
    Activations Density 0.008%

    No Known Activations