© 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. 206504
    Prev
    Next
    INDEX
    Explanations

    HD video conferencing, UK business hours, weekly client meetings

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

    "Say" or "safe"

    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
    د
    0.45
    яза
    0.45
    )~
    0.44
    husband
    0.43
     وچ
    0.42
    scales
    0.42
     پرون
    0.42
    鱗
    0.41
    scorpion
    0.41
    rhinoceros
    0.41
    POSITIVE LOGITS
    inti
    0.50
    гности
    0.47
     continue
    0.46
    mond
    0.45
     <
    0.44
     过
    0.43
    oint
    0.43
     ấn
    0.42
    న్ని
    0.42
    дем
    0.42
    Activations Density 0.000%

    No Known Activations