© 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. 28801
    Prev
    Next
    INDEX
    Explanations

    achieve better, fenced yard, pure choreographed

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

    cultures, vehicles, rivalry, called

    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
     პრო
    0.44
    🫠
    0.44
    ☯
    0.42
    時期
    0.42
     uiteindelijk
    0.42
     réessayer
    0.41
     പ്രദേശ
    0.40
    laşı
    0.40
     ambientes
    0.40
     logika
    0.40
    POSITIVE LOGITS
     avoir
    0.45
     because
    0.45
     importance
    0.43
     。
    0.43
    。
    0.42
    .
    0.42
     不需要
    0.42
     aquella
    0.41
    because
    0.41
     remove
    0.41
    Activations Density 0.000%

    No Known Activations