© 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. 189077
    Prev
    Next
    INDEX
    Explanations

    isotopic composition, directed to, entire screen, understand what

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

    safety and alignment protocols

    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
    abulous
    0.50
    nem
    0.48
    premier
    0.48
    -}
    0.47
    acha
    0.46
     মিঃ
    0.46
    da
    0.45
    FN
    0.44
    democratic
    0.44
    awal
    0.43
    POSITIVE LOGITS
     sản
    0.48
     Übers
    0.44
     furnishes
    0.43
     personer
    0.43
     επισ
    0.43
    产
    0.42
     admon
    0.42
     gdyż
    0.42
    娱乐圈
    0.42
    บวน
    0.42
    Activations Density 0.001%

    No Known Activations