© 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. 31175
    Prev
    Next
    INDEX
    Explanations

    non-toxic, crave, locate

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

    nicotine or ETH

    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
    ဉ်
    0.53
    όμε
    0.52
    时
    0.50
    游客
    0.49
    Naming
    0.49
    ман
    0.48
     позволит
    0.47
    高志森
    0.47
    锣
    0.46
    ெய்
    0.45
    POSITIVE LOGITS
     suspected
    0.54
     insanely
    0.54
     skyrocketed
    0.52
     pernicious
    0.51
     आज
    0.51
     Rohingya
    0.49
     دارم
    0.48
     ನಾನು
    0.47
     Algon
    0.47
    😭
    0.47
    Activations Density 0.000%

    No Known Activations