© 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. 68203
    Prev
    Next
    INDEX
    Explanations

    harmful chemicals and percentages

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

    English, elaborate, completely, very

    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
     📫
    0.54
     временем
    0.53
    ූප
    0.53
    где
    0.52
     電力
    0.52
     запад
    0.52
     времени
    0.51
     места
    0.51
    𝑮
    0.51
    ходит
    0.50
    POSITIVE LOGITS
     retailer
    0.49
    television
    0.48
     NYC
    0.47
     television
    0.46
     Television
    0.45
     televisie
    0.44
     ceramics
    0.43
     Currie
    0.43
    tank
    0.43
     POM
    0.42
    Activations Density 0.001%

    No Known Activations