© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 89024
    Prev
    Next
    INDEX
    Explanations

    users to about, thinking about

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

    considering, likely, intent, potentially, style, problem, demand

    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
    めちゃ
    0.52
    spersed
    0.50
    travel
    0.50
    ningarna
    0.49
    毎
    0.48
    ご覧
    0.48
    telling
    0.46
    ਆਂ
    0.46
    sthe
    0.46
    は
    0.45
    POSITIVE LOGITS
     wrong
    0.52
     Jovan
    0.47
     Kama
    0.44
     Schultz
    0.43
     konflikt
    0.43
     Komponenten
    0.42
     buruk
    0.42
     inconsistency
    0.42
     negatif
    0.42
    সিদ্ধ
    0.41
    Activations Density 0.001%

    No Known Activations