© 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. 86166
    Prev
    Next
    INDEX
    Explanations

    dating profile headlines

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

    predicting future events

    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
     verloren
    0.43
    Fernseh
    0.40
     province
    0.40
    ר
    0.40
     Keb
    0.39
    عيب
    0.39
    ويم
    0.39
    ServletException
    0.38
     spouse
    0.38
    جن
    0.38
    POSITIVE LOGITS
     डैश
    0.51
     τη
    0.49
     እንዴት
    0.49
     başlayalım
    0.48
    綰
    0.47
    टेन
    0.47
     ಸರಿಯ
    0.47
     केंद्रा
    0.46
     लिव
    0.46
     पाउडर
    0.46
    Activations Density 0.001%

    No Known Activations