© 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. 91943
    Prev
    Next
    INDEX
    Explanations

    describe perception of reality

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

    brain-created reality maps

    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
     cravings
    0.51
     skyrocketed
    0.48
     penchant
    0.47
     मैं
    0.46
     मैंने
    0.46
     mujhe
    0.45
     nonostante
    0.45
     我
    0.45
     souhaitez
    0.44
    我还
    0.44
    POSITIVE LOGITS
     বিবরণ
    0.47
     COLLATION
    0.47
     интерпре
    0.45
     crucially
    0.44
     LOCAL
    0.44
     этими
    0.43
    ева
    0.43
    КО
    0.42
    看到的
    0.41
     уточ
    0.41
    Activations Density 0.007%

    No Known Activations