© 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. 249388
    Prev
    Next
    INDEX
    Explanations

    students andmascot!susceptible topaper andIT firm

    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
    ة
    0.46
     entertainer
    0.45
    4
    0.45
     estiver
    0.43
    釜
    0.42
    ɣ
    0.41
     entreten
    0.39
    成
    0.39
     priorité
    0.39
    
    0.38
    POSITIVE LOGITS
     ड्राइव
    0.52
    ৌত
    0.50
    ometimes
    0.48
    ितीय
    0.48
    oints
    0.47
    ందూ
    0.47
     คลิ
    0.46
    larından
    0.46
    rishna
    0.46
    ually
    0.46
    Activations Density 0.000%

    No Known Activations