© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11252
    Prev
    Next
    INDEX
    Explanations

    case studies, slide decks, prototype drugs

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

    question marks and formatting

    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_40_width_16k_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
    sib
    0.46
     fidd
    0.45
     săptăm
    0.42
    ně
    0.42
    Sib
    0.42
    Symfony
    0.42
    ꧁
    0.40
     phần
    0.40
     Xmas
    0.40
    fixtures
    0.40
    POSITIVE LOGITS
     FIGURE
    0.57
    FIGURE
    0.48
     OBJECT
    0.47
     ■
    0.46
     CASES
    0.46
    ■
    0.46
    思考
    0.45
     THINK
    0.45
     ▼
    0.45
     Integrative
    0.45
    Activations Density 0.051%

    No Known Activations